how to write a research paper with chat gpt

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• J Pediatr Pharmacol Ther
• v.28(6); 2023
• PMC10731938

ChatGPT for Research and Publication: A Step-by-Step Guide

Som s. biswas.

Department of Pediatric Radiology, Le Bonheur Children’s Hospital, The University of Tennessee Health Science Center, Memphis, TN.

Introduction

This commentary provides a concise step-by-step guide on using ChatGPT, an advanced natural language processing (NLP) model, for research and publication purposes. The guide assesses crucial aspects, including data preprocessing, fine-tuning techniques, prompt engineering, and ethical considerations. By addressing challenges related to biases, interpretability, and plagiarism, this commentary offers insights and recommendations for the responsible and ethical use of ChatGPT. The guide empowers researchers to ethically integrate ChatGPT effectively into their workflows, enhancing productivity and improving the quality of their scientific publications. Through clear instructions and guidelines, researchers can tap into the transformative potential of ChatGPT, driving scientific progress in a language-driven world.

In recent years, the field of NLP has witnessed remarkable advancements, bringing us closer to the realm of humanlike language generation. Among these advancements, ChatGPT, based on the groundbreaking GPT-3.5 architecture developed by OpenAI, stands as an impressive language model capable of generating coherent and contextually relevant text responses. With its ability to understand and respond to user inputs, ChatGPT has opened up new possibilities for various applications, including research and publication. 1 – 3

The traditional process of conducting research and publishing scientific papers has been significantly transformed by the emergence of ChatGPT. Researchers and authors can now leverage the power of this sophisticated language model to streamline and enhance their workflow, leading to improved efficiency and higher-quality publications. However, using ChatGPT effectively in the research and publication domain requires a comprehensive understanding of its capabilities, limitations, and best practices.

In this commentary I offer my thoughts for a step-by-step guide for researchers and authors who seek to harness the potential of ChatGPT in their research endeavors and publication efforts. By exploring various aspects, such as data preprocessing, fine-tuning techniques, prompt engineering, and ethical considerations, this guide will equip researchers with the necessary knowledge to harness the full potential of ChatGPT in their scientific pursuits. Moreover, this commentary will delve into the challenges associated with using ChatGPT for research and publication, including biases, interpretability, and concerns regarding plagiarism. By addressing these challenges directly, I aim to provide researchers with valuable insights and recommendations to navigate these important issues and ensure the responsible and ethical use of ChatGPT as a research tool. 4

The significance of my guide lies in its potential to bridge the gap between the rapid progress of language models like ChatGPT and the research and publication process. By elucidating the intricacies of integrating ChatGPT into scientific workflows, researchers will be empowered to leverage this advanced technology effectively, thereby enhancing the overall quality and impact of their research output. 5 In the following sections, I present a comprehensive overview of the steps involved in using ChatGPT for research and publication.

Step 1: Title and Title Page Creation by ChatGPT

ChatGPT can be a valuable tool in generating titles for research papers. Its ability to understand and generate humanlike text allows it to analyze and synthesize information provided by researchers to craft concise and impactful titles. By leveraging its vast knowledge base and language capabilities, ChatGPT can assist in capturing the essence of a research paper, conveying the main focus and contributions succinctly. Researchers can collaborate with ChatGPT by providing relevant information, such as the subject, objectives, methodology, and key findings of their study. ChatGPT can then generate multiple title options, offering different perspectives and angles that researchers can consider. This collaboration with ChatGPT can save time and stimulate creativity, helping researchers refine their titles to accurately represent their work and engage potential readers. ChatGPT can then be used to create the entire title page and then can also customize based on each journal’s recommendations.

For example:

Thus, we see that ChatGPT can write an entire title page based on just the title and author details. We notice that ChatGPT has created an email address that is incorrect and needs manual rectification. However, the rest of the title page, including keywords and the running title, is appropriate.

Step 2: Abstract/Summary Creation by chatGPT

ChatGPT can assist in condensing complex information into a clear and engaging abstract/summary, helping researchers communicate the significance and novelty of their research to a wider audience. By leveraging the language proficiency of ChatGPT, researchers can save time and effort in crafting abstracts while ensuring that the key aspects of their study are accurately represented.

In this example, we demonstrate that ChatGPT can create an entire abstract just by using the title alone. However, the more information researchers provide (preferably the entire body of the paper should be entered into chatGPT), the more accurate the abstract becomes.

Step 3: Introduction Creation by ChatGPT

By collaborating with ChatGPT, researchers can provide key information, such as the background, significance, and objectives of their study. ChatGPT can then generate a well-structured introduction that sets the context, highlights the relevance of the research, and outlines the paper’s objectives. Also, ChatGPT can be used to generate keywords and generate an abbreviations list from the article by using prompts. However, it is important to note that the generated introduction should be reviewed, customized, and refined by the researchers to align with their specific study and writing style.

In the example below, we note that ChatGPT has not only created an introduction but also the objectives of the study, which can then be edited by the human author.

Step 4: Can ChatGPT Create a Literature Review?

Yes, ChatGPT can help generate a literature review, but it is important to note that it may not have access to the most up-to-date research articles and studies due to copyrights and limited access to some journals. Additionally, a literature review typically requires a comprehensive analysis of multiple sources, so the generated response may not cover all relevant studies. Nonetheless, it can assist in providing a basic literature review on a given topic, which will need human authors to add to and edit it.

As we can see, ChatGPT is not as good at giving a detailed review of the literature as it is at summarizing contents or creating an introduction. Thus, its use is limited, if there is any at all, in this section of the paper.

Step 5: Can ChatGPT Assist in Brainstorming the Methodology of Studies?

ChatGPT can be a helpful tool in conceptualizing the methodology for research papers. By engaging in a conversation with ChatGPT, researchers can discuss their research objectives, study design, data collection methods, and data analysis techniques. ChatGPT’s natural language understanding allows it to provide suggestions and insights based on its knowledge base and understanding of research methodologies. Although ChatGPT can assist in generating ideas and providing guidance, it is important for researchers to critically evaluate and adapt the suggestions to align with their specific research goals and requirements.

Although the methodology is something that is unique to each paper and needs a human researcher to conceptualize it, we see in this example that ChatGPT can assist by giving ideas and examples based on the input of the title by the human researcher. Thus, ChatGPT can be part of brainstorming sessions when conceptualizing a study, although this section needs significant editing by a human, unlike the introduction or summary.

Step 6: Do Not Use ChatGPT for Fabricating Patient Data or Results!

This section of the paper must be authentic, and ChatGPT has a limited role, if any, because patient data have to be original. ChatGPT also currently cannot analyze clinical data compared with statistical software, like SPSS Statistics and Base SAS. However, Microsoft appears to be developing an Excel copilot that uses AI to create graphs and plots, and its use needs to be evaluated once it is released to the public. 6

Step 7: Discussion and Conclusions

This section of the paper can be generated by ChatGPT if all results are pasted as input; however, this section also needs manual editing because inaccuracies are common. By discussing their research with ChatGPT, researchers can also identify potential limitations, discuss the broader implications of their findings, and propose future research directions. Although ChatGPT can generate suggestions and facilitate the thought process, it is important for researchers to critically evaluate the information provided and ensure that the Discussion and Conclusion sections align with the specific research objectives and findings of their study. Ultimately, ChatGPT can serve as a supportive tool in developing a comprehensive and well-rounded discussion and conclusion for research papers.

Step 8: References

As per the author's experience, although ChatGPT is capable of creating references for an article, most of them are incorrect. So, using ChatGPT for creating references is not recommended. However, ChatGPT can convert references into any journaling style if the references are entered into ChatGPT and it is asked to convert them into a specific style.

Disadvantages of Using ChatGPT in Research

Although ChatGPT offers numerous advantages for assisting in the writing of research papers, there are also some important potential disadvantages to consider:

• Lack of domain expertise: ChatGPT is a general-purpose language model trained on a diverse range of Internet text, which means it may lack the specific domain expertise required for certain research topics. It may generate responses that are not accurate or well informed in specialized fields, potentially leading to incorrect or misleading information in research papers.
• Inconsistency and variability: ChatGPT’s responses can be inconsistent and vary depending on the input phrasing or prompt formulation. This can lead to unpredictability in generating reliable and coherent content, requiring additional effort to refine and ensure accuracy in research papers.
• Limited control over output: Although researchers can guide the model’s responses through prompts, ChatGPT’s generation process is still primarily autonomous. Researchers have limited control over the precise content and structure of the generated text, which may require careful editing and review to align with specific research goals, standards, and above all, accuracy.
• Biases and ethical considerations: Language models like ChatGPT can inadvertently reflect biases present in the training data. These biases may perpetuate existing societal or cultural biases in research papers, potentially leading to unfair or discriminatory content. The careful examination and mitigation of biases are crucial to ensure ethical and unbiased research output. 7
• Lack of interpretability: ChatGPT’s decision-making process is complex and not easily interpretable. Researchers may struggle to understand the reasoning behind the model’s generated responses, making it challenging to assess the reliability and credibility of the information provided. Ensuring transparency and interpretability in research papers becomes more challenging with such models. ChatGPT should cite the sources for its data, like Google Bard does.
• Plagiarism concerns: Because of its vast training data from the Internet, ChatGPT may inadvertently generate text that resembles or replicates existing content without proper citation or attribution. Researchers must be cautious about unintentional plagiarism and ensure that generated content is appropriately referenced and original. So, all ChatGPt-generated articles need to be double checked using antiplagiarism software.

In this commentary I have provided a comprehensive step-by-step guide for researchers and authors on harnessing the power of ChatGPT in the realm of research and publication. By exploring crucial aspects, such as data preprocessing, fine-tuning techniques, prompt engineering, and ethical considerations, the guide equips researchers with the necessary knowledge and tools to effectively integrate ChatGPT into their scientific workflows. 8

Through clear instructions, examples, and guidelines, researchers can navigate the complexities of using ChatGPT, leading to enhanced productivity and improved quality in their research output. Moreover, I address the challenges associated with biases, interpretability, and plagiarism concerns, ensuring the responsible and ethical usage of ChatGPT as a research tool.

The significance of this research lies in its ability to bridge the gap between the rapid advancements in language models like ChatGPT and the research and publication process. By empowering researchers with the skills to leverage ChatGPT effectively, this guide fosters innovation, drives scientific progress, and opens up new possibilities for transformative contributions to various fields. 9

As language-driven technologies continue to evolve, researchers must stay abreast of the latest advancements and best practices. The step-by-step guide presented in this commentary serves as a valuable resource, providing researchers with the knowledge and guidance necessary to maximize the potential of ChatGPT in their research endeavors. By embracing the capabilities of ChatGPT and ensuring its responsible and ethical use, researchers can revolutionize the way research and publications are conducted. With ChatGPT as a powerful tool in their arsenal, researchers are poised to make significant strides in their respective fields, pushing the boundaries of scientific knowledge and ushering in a new era of language-driven innovation. 10

However, and to reiterate, I cannot overemphasize that ChatGPT has, at present, many disadvantages, including inconsistencies, bias, and plagiarism concerns, that must be addressed by the human author before the article is submitted for publication to a journal, as well as prior to publication, because the human author(s) is solely responsible for their research integrity and accurate reporting.

In conclusion, I have attempted to provide researchers with a comprehensive understanding of how to effectively leverage ChatGPT for research and publication purposes. It has also highlighted the problems and precautions that the human author(s) must take before publishing ChatGPT-generated content. By embracing this step-by-step guide, researchers can unlock the full potential of ChatGPT, driving scientific progress and shaping the future of research and publications.

• Please use ChatGPT only if allowed by your institution, research lab, and the journal in question.
• Please acknowledge ChatGPT within your manuscript/published paper wherever you are using it.
• Please do not fabricate or plagiarize data. ChatGPT can be used only for summarizing texts, improving English writeups, and brainstorming ideas, and not for creating fabricated research raw data.

Acknowledgment.

The author acknowledges that this article was partially generated by ChatGPT (powered by OpenAI’s language model, GPT-3; http://openai.com ). The editing was performed by the human author.

Disclosures. The author declare no conflicts or financial interest in any product or service mentioned in the manuscript, including grants, equipment, medications, employment, gifts, and honoraria.

Home → Academic Writing → How to Use ChatGPT to Write a Research Paper: Tips and Tricks to Get You Started

How to Use ChatGPT to Write a Research Paper: Tips and Tricks to Get You Started

Jordan Kruszynski

• January 4, 2024

If you’re an academic, you’ve probably spent a lot of time planning and writing research papers. It’s a fine art, and one that requires a fair amount of skill, precision and preparation. But whether you’re an old master in the field, or a rookie embarking on your first serious research paper, there are tools that can help you to simplify the planning stages and organise your thoughts more effectively.

One of those tools is the (in)famous ChatGPT , and it’s this that we’ll be focusing on in our article. In the right hands, ChatGPT can become a powerful research tool that will make your paper-writing that little bit easier. So sit back, relax, and discover our tips and tricks for using ChatGPT to write a research paper.

What is ChatGPT?

Just in case you don’t already know, ChatGPT is an artificial intelligence tool developed by OpenAI that can help you with your research. It uses natural language processing to understand what you’re looking for and provide you with relevant information. You can ask it questions, and it will provide you with answers in a conversational style, as well as offer sources to back up its information.

One of the biggest advantages of ChatGPT is that it can save you time. Instead of spending hours searching for sources, you can simply ask ChatGPT for help. This can bring you a reliable list of sources for further investigation fairly quickly. It’s crucial to note however that the AI shouldn’t be exploited to do the actual writing of the paper for you. This could see you accused of plagiarism or misconduct, and besides, as a researcher, you’re probably rightfully proud of your ability to write a compelling paper.

Another advantage of ChatGPT is that it’s always available (even when libraries or other sources of information might be inaccessible) so you can work on your research paper at any time of day or night.

Interested in learning more about how AI programs like ChatGPT are changing the academic landscape? Listen to Oxford researcher Samantha-Kaye Johnston’s views from the frontline in this exciting episode of The Research Beat podcast.

The benefits of using ChatGPT to write a research paper

There are many benefits to using ChatGPT for research papers. Firstly, as we mentioned earlier, it can save you time . A slow drag of several hours looking for specific sources can be reduced to just a few minutes with the AI’s help.

Secondly, it can help you find sources that you might not have found otherwise . ChatGPT has access to a wide range of sources, including academic journals and books.

Thirdly, it can help you organise your research . ChatGPT can provide you with a summary of the information you’ve gathered, making it easier to analyse and integrate into your research paper.

How to use ChatGPT to write a research paper – a step by step guide

• Start by creating a list of questions that you want to answer in your research paper.
• Open ChatGPT and ask it one of the questions on your list, for example, ‘What is the critical history of feminist literature in Europe?’
• ChatGPT will provide you with a list of sources to check out.
• Read through the sources and take notes on the information that is relevant to your research question.
• Repeat steps 2-4 for each question on your list.
• Once you’ve gathered all of your information, organise it into an outline for your research paper.
• Use the information you’ve gathered to write your research paper.

Working with your sources

Once you have your sources in order, you might want to use prompts to get help from ChatGPT with other parts of the writing process. A prompt is a specific instruction to the AI that can give you tailored information or responses. For example, if you’re struggling to understand part of another research paper, you could use the following prompt:

‘Please explain the following paragraphs in simple words. I am having trouble understanding (insert concept here).’

Input the prompt along with the relevant passage from the source, and ChatGPT will provide a summary that could help you to unlock your understanding of the tricky concept.

Looking for ChatGPT prompts tailor-made for academics? Check out Audemic’s list of over 50 prompts to help you with your work and research!

Writing tips and tricks for using ChatGPT

When using ChatGPT to write a research paper, it’s important to keep a few things in mind. Firstly, make sure that you’re using reliable sources . ChatGPT can provide you with a list of sources, but it’s up to you to determine which ones are reliable.

Secondly, make sure that you’re paraphrasing the information you’ve gathered in your own words . You don’t want to cheat or be accused of it.

Finally, make sure that you’re using the information you’ve gathered to answer your research questions . Everything you uncover through ChatGPT should be used to feed your own understanding and improve the quality and precision of your answers.

Common mistakes to avoid when using ChatGPT to write a research paper

While ChatGPT is an excellent tool for research papers, there are some common mistakes to avoid:

• Crucially, don’t rely too heavily on ChatGPT. It’s essential to do some of your research on your own and use ChatGPT to supplement it.
• Don’t forget to cite your sources correctly. Just because ChatGPT provided you with the information doesn’t mean that you don’t need to cite it. Moreover, ChatGPT cannot actually produce academic citations for you.
• Always remember to proofread your research paper carefully, especially if you’ve used AI elements to construct it.

ChatGPT vs. traditional research methods

While traditional research methods have their advantages and always will, ChatGPT, as we’ve seen, has some of its own. We think one of the best uses for AI programs like ChatGPT is to accelerate parts of the paper-writing process that would otherwise take hours. If you can use the AI to produce a list of interesting and relevant sources, then you can get to work quickly as an academic, studying and analysing those sources to determine their value within your paper. In general, if you approach ChatGPT with an attitude of maintaining quality and integrity, then it can only enhance your work.

Final Thoughts

ChatGPT is everywhere at the moment, and while it has stirred up a great deal of controversy thanks to its implications for academic integrity, it can be an excellent tool for helping to write research papers . The key is using it correctly, and not relying too heavily on it. Focusing on how it can enhance your already-sharp academic writing skills will allow you to save time, find plenty of valuable sources, and organise your paper’s structure more effectively. And that’s how to use ChatGPT to write a research paper!

ChatGPT is not the only AI tool that can help with these parts of the paper-writing puzzle. If you want to listen to academic papers, break them down into digestible pieces and freely take notes on them, then Audemic is waiting for you. Try it for free today!

Keep striving, researchers! ✨

Table of Contents

Related articles.

How to Publish a Research Paper: A Step-by-Step Guide

You’re in academia. You’re going steady. Your research is going well and you begin to wonder: ‘How exactly do I get a

Behind the Scenes: What Does a Research Assistant Do?

Have you ever wondered what goes on behind the scenes in a research lab? Does it involve acting out the whims of

How to Write a Research Paper Introduction: Hook, Line, and Sinker

Want to know how to write a research paper introduction that dazzles? Struggling to hook your reader in with your opening sentences?

Blog Podcast

Privacy policy Terms of service

Subscribe to our newsletter!

Discover more from Audemic: Access any academic research via audio

Subscribe now to keep reading and get access to the full archive.

Type your email…

Continue reading

Navigation Menu

Search code, repositories, users, issues, pull requests..., provide feedback.

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications You must be signed in to change notification settings

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

ahmetbersoz/chatgpt-prompts-for-academic-writing

Folders and files, repository files navigation.

✨ NEW UPDATE: Literature Review Generator

A Custom GPT for Literature Review Generator has been released. It efficiently parses PDF files of research publications, extracts key themes, and creates a literature review section for your academic publications.

TRY NOW: https://chat.openai.com/g/g-G3U8pZGwC-literature-review-generator

ChatGPT Prompts for Academic Writing

In this repository, this list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans. Whether you're a student, researcher, or academic professional, these prompts can help you hone your writing abilities and tackle your writing projects with confidence.

Use directly in: chat.openai.com

The list is regularly updated, so you can keep track of new prompts by following this repository.

TIPS: As there is a limit to the number of words that can be used in ChatGPT, you can input your text multiple times using the prompt "Read this [PARAPGRAPH]:" and then run your final prompt "Considering the above text...".

You can also use prompts splitter: chatgpt-prompt-splitter.jjdiaz.dev

BRAINSTORMING

Article sections, title/topic sentence, introduction, literature review.

NOTE: Be careful and double-check article existence. ChatGPT may generate fake references

Methodology

Experiments, future works, improving language, summarization, plan/presentation, working with documents (available only in gpt-4).

Upload a PDF file of a paper then:

Upload a PDF file of your paper then:

Upload PDF files of papers then:

Upload a figure image then:

Contributors 4

How To Use ChatGPT To Write A Literature Review: Prompts & References

In the rapidly evolving world of academic research, the integration of AI tools like ChatGPT has transformed the traditional approach to literature reviews. As a researcher, you should also leverage on this tool to make your research work easier.

In this post, explore how ChatGPT can enhance the literature review process. We’ll explore how specific prompts can effectively guide this advanced AI model to generate insightful content, while ensuring accuracy, relevance, and academic integrity in their scholarly work.

How to Use ChatGPT for Writing a Literature Review

Understanding chatgpt’s limitations.

While it can efficiently generate content, streamline the research process, and provide a comprehensive understanding of relevant literature, its capabilities are not without constraints. Here are some for you to consider:

Dependence On Pre-Existing Datasets

Since ChatGPT is a language model trained on available data, it may not include the most recent research papers or cutting-edge findings in a specific field. This gap can lead to a lack of current state-of-research insights, particularly crucial in fields like technology and science where advancements happen rapidly.

May Lack Depth And Context

ChatGPT, while able to produce summaries and synthesize information, might not fully grasp the nuanced arguments or complex theories specific to a research topic. This limitation necessitates that researchers critically evaluate and supplement AI-generated text with thorough analysis and insights from recent systematic reviews and primary sources.

Risk Of Plagiarism

Although ChatGPT can generate human-like text, it’s vital to ensure that the content for your literature review is original and properly cited. Relying solely on ChatGPT to write a literature review defeats the purpose of engaging deeply with the material and developing a personal understanding of the literature.

Not A Total Replacement of A Researcher

While ChatGPT can assist non-native English speakers in crafting clear and concise academic writing, it’s not a replacement for the human ability to contextualize and interpret research findings. Researchers must guide the AI model with specific prompts and leverage it as a tool rather than a substitute for comprehensive analysis.

By keeping these limitations in mind, ChatGPT can be a valuable aid in the literature review process, but it should be used judiciously and in conjunction with traditional research methods.

Defining Research Objective

When starting on writing a literature review, the initial step involves using ChatGPT to define your research question or hypothesis.

The AI model’s ability to respond with a summary of the current state of research in your field can provide a comprehensive understanding, especially for systematic reviews or research papers.

For example, by inputting a prompt related to your research topic, ChatGPT can generate human-like text, summarizing prior research and highlighting relevant literature.

One insider tip for effectively using ChatGPT in the literature review process is to leverage its natural language processing capabilities to identify relevant keywords.

These keywords are crucial for non-native English speakers or those new to a research field, as they streamline the search for pertinent academic writing. Additionally, ChatGPT can guide you in understanding the context of your research topic, offering insights that are often challenging to find.

Using AI language models like ChatGPT for generating content for your literature review is efficient and effective, saving valuable time. However, it’s vital to critically evaluate the generated text to ensure it aligns with your research objectives and to avoid plagiarism.

ChatGPT’s ability to synthesize large amounts of information can aid in developing a clear and concise outline, but remember, it’s a guide, not a replacement for human analysis.

Despite these limitations, ChatGPT provides a unique advantage in conducting literature reviews. It can automate mundane tasks, allowing researchers to focus on analysis and critical thinking.

Identifying Keywords and Search Terms

Using ChatGPT to identify relevant keywords related to your research topic can significantly streamline your workflow.

For instance, when you input a summary of your research question into ChatGPT, the AI model can generate a list of pertinent keywords.

These keywords are not just randomly selected; they are based on the vast amounts of information in ChatGPT’s dataset, making them highly relevant and often inclusive of terms that are current in your research field.

An insider tip for leveraging ChatGPT effectively is to guide the AI with clear and concise prompts.

For example, asking ChatGPT to: “summarize key themes in [specific field] research papers from the last five years” can yield a list of keywords and phrases that are not only relevant but also reflective of the current state of research.

This approach is particularly beneficial for conducting systematic reviews or for non-native English speakers who might be unfamiliar with specific academic jargon.

While ChatGPT can provide a comprehensive understanding of relevant literature and help automate the identification of keywords, it’s important to critically evaluate the generated content.

Researchers should use ChatGPT as a tool to augment their research process, not as a replacement for human insight.

It’s crucial to mind the limitations of the AI model and ensure that the keywords identified align with the research topic and objectives.

Creating an Initial Literature Review Outline

The key to using ChatGPT effectively in crafting an initial outline lies in its ability to generate content based on specific prompts.

For instance, a researcher working on organic photovoltaic devices can input a prompt into ChatGPT, such as “Help me create a structure for a literature review on organic photovoltaic devices.”

The AI model, using its comprehensive understanding of the research topic, can then produce a preliminary structure, including sections like:

• Introduction
• Advances in materials and technology, performance, and efficiency.

This generated outline serves as a valuable starting point. It helps in organizing thoughts and determining the key areas that the literature review should cover. I

mportantly, researchers can refine and expand this initial outline as they delve deeper into their topic, ensuring it aligns with their specific research question and the current state of research.

However, while ChatGPT can streamline the review process and save valuable time in creating an initial outline, researchers should not solely rely on it.

The content generated by ChatGPT must be critically evaluated and supplemented with in-depth research. This involves:

• Reading systematic reviews
• Reading research papers, and
• Summarizing relevant literature to ensure the review is comprehensive and up-to-date.

Get ChatGPT To Help You During Research, Using The Right Prompts

The key to effectively using ChatGPT in this process lies in crafting the right prompts, guiding the AI to generate relevant and useful content. 

When initiating a literature review, the prompt should aim for a broad understanding of the research topic. For instance, asking ChatGPT to:

• “Give a brief overview of research done on [topic]”
• “What are some of the recent findings on the [topic] in research?” or 
• “Summarize the historical development of [topic] in academia”

Helps in capturing the general landscape of the field. These prompts assist in identifying key theories, methodologies, and authors within the research area. As the review progresses, more specific prompts are necessary to delve deeper into individual studies. Queries like:

• “Summarize the main arguments and findings of [specific paper]” or
• “What are the strengths and weaknesses of [specific paper]?”

enable ChatGPT to provide detailed insights into particular research papers, aiding in understanding their contribution to the broader field. Comparative prompts are also crucial in synthesizing information across multiple works. Asking ChatGPT to:

• “Compare and contrast the methodologies of [paper 1] and [paper 2]” or
• “How do the findings of [paper 1] and [paper 2] agree or disagree?”

helps in discerning the nuances and disparities in the literature. In the final stages of the literature review, prompts should focus on summarizing findings and identifying emerging trends or gaps. For example:

• “What trends or patterns have emerged from the literature on [topic]?” or
• “What future research directions are suggested by the literature on [topic]?”

We will share more on these ChatGPT prompts in the later part of this post, read on.

Reviewing ChatGPT’s Responses

When using ChatGPT to write a literature review, it’s crucial to critically evaluate its responses.

Firstly, researchers should cross-reference the information provided by ChatGPT with actual research papers.

This step ensures the accuracy of the data and helps in identifying any discrepancies or outdated information, given that ChatGPT’s dataset may not include the most recent studies.

Another essential aspect is assessing the coherence and depth of the AI-generated text. ChatGPT can summarize and synthesize information efficiently, but it might not capture the nuances of complex theories or research arguments.

Researchers should ensure that the content aligns with their research question and systematically reviews the topic comprehensively. This is where a researcher’s value comes in.

Additionally, verifying the originality of the content is vital to avoid plagiarism. While ChatGPT can generate human-like text, researchers must ensure that the AI-generated content is used as a guide rather than a verbatim source. 

Proper citations and references are essential to maintain the integrity of the literature review. Avoid torpedoing your own research by committing plagiarism.

Ensuring Coherence and Flow

One of the challenges when using such advanced AI language models is ensuring the coherence and flow of the final document. This aspect is crucial as it determines the readability and academic rigor of the literature review.

ChatGPT can generate vast amounts of content on a wide range of topics, responding efficiently to prompts and synthesizing information from its extensive dataset.

However, the content generated by ChatGPT, while informative, might not always align seamlessly with the specific research question or maintain a consistent narrative flow.

To tackle this, researchers need to take an active role in guiding ChatGPT and subsequently refining its output.

A practical approach is to use ChatGPT as a starting point, leveraging its ability to quickly provide summaries, synthesize relevant literature, and identify key references and keywords related to the research topic. For example, prompts like:

• “Summarize the current research on [topic]” or
• “Identify key debates in [topic]”

Can yield valuable initial insights.

Once this foundational information is obtained, the crucial task is to carefully review and edit the AI-generated content.

This involves connecting the dots between different sections, ensuring that each part contributes meaningfully to addressing the research question, and refining the language to maintain academic standards.

It’s also essential to check for and avoid plagiarism, ensuring that all sources are correctly cited.

In addition, considering the vast amounts of information ChatGPT can access, it’s vital to verify the accuracy and relevance of the content.

Researchers should cross-reference AI-generated summaries with actual research papers, especially the most recent ones, as ChatGPT’s dataset may not include the latest studies.

Editing and Proofreading

Now that your literature review is mostly written out, now focus on the editing and proofreading. The content generated by ChatGPT needs to be meticulously reviewed and edited. Here are the steps:

• Verifying the accuracy of the information. Researchers must cross-check the AI-generated content against actual research papers and systematic reviews. This ensures that the latest studies are accurately represented.
• Improve coherence and flow. Researchers should restructure sentences, ensure logical progression of ideas, and maintain a consistent academic tone throughout the document.
• Checking for plagiarism. Despite ChatGPT’s ability to generate human-like text, researchers must ensure that all sources are correctly cited and that the review does not inadvertently replicate existing material.
• Check Grammar and Spelling: Editing should encompass grammar checks, vocabulary refinement, and ensuring that the language used is appropriate for an academic audience.
• Update Citation: Review citation, or reference list to ensure everything is cited correctly, and the citation list is written out to your required standard, be it MLA, Chicago, or APA.

What ChatGPT Prompts To Use When Writing A Literature Review?

There are many ways to use ChatGPT to write literature review, usually by using the right prompts. Here’s how specific types of prompts can be effectively employed, with multiple examples for each category:

• “Provide a comprehensive overview of the latest research on [topic].”
• “Summarize the current understanding and key findings in the field of [topic].”
• “Detail the dominant theoretical frameworks currently used in [topic].”
• “Describe the evolution of theoretical approaches in [topic] over the past decade.”
• “Identify and discuss the major debates or controversies in [topic].”
• “What are the conflicting viewpoints or schools of thought in [topic]?”
• “List the leading researchers in [topic] and summarize their key contributions.”
• “Who are the emerging authors in [topic], and what unique perspectives do they offer?”
• “Explain the most common research methodologies used in studies about [topic].”
• “How have the methodologies in [topic] research evolved recently?”
• “Trace the historical development and major milestones in [topic].”
• “Provide a timeline of the key discoveries and shifts in understanding in [topic].”
• “What significant paradigm shifts have occurred in [topic] in the last twenty years?”
• “How has the focus of research in [topic] changed over time?”
• “Analyze the methodology and conclusions of [specific paper].”
• “Discuss the impact and reception of [specific paper] in the field of [topic].”
• “Compare the results and methodologies of [paper 1] and [paper 2] in [topic].”
• “How do [paper 1] and [paper 2] differ in their approach to [topic]?”
• “Based on current literature, what are the suggested future research directions in [topic]?”
• “Identify gaps in the literature of [topic] that could be explored in future studies.”

By using these types of prompts, researchers can guide ChatGPT to produce content that is not only relevant to their literature review but also rich in detail and scope.

Wrapping Up: Use Other AI Tools Too, Not Just ChatGPT

In conclusion, while ChatGPT serves as a powerful ally in the literature review process, it’s important to recognize it as one of many AI tools available to researchers as well. Diversifying your AI toolkit can enhance the depth and breadth of your review, offering varied perspectives and methodologies.

As AI continues to evolve, embracing a range of these tools can lead to more comprehensive, nuanced, and innovative academic writing, expanding the horizons of research and scholarly exploration beyond what we currently envision.

Dr Andrew Stapleton has a Masters and PhD in Chemistry from the UK and Australia. He has many years of research experience and has worked as a Postdoctoral Fellow and Associate at a number of Universities. Although having secured funding for his own research, he left academia to help others with his YouTube channel all about the inner workings of academia and how to make it work for you.

Thank you for visiting Academia Insider.

We are here to help you navigate Academia as painlessly as possible. We are supported by our readers and by visiting you are helping us earn a small amount through ads and affiliate revenue - Thank you!

2024 © Academia Insider

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• 07 July 2023
• Correction 11 July 2023

Scientists used ChatGPT to generate an entire paper from scratch — but is it any good?

• Gemma Conroy

You can also search for this author in PubMed   Google Scholar

A pair of scientists has produced a research paper in less than an hour with the help of ChatGPT — a tool driven by artificial intelligence (AI) that can understand and generate human-like text. The article was fluent, insightful and presented in the expected structure for a scientific paper, but researchers say that there are many hurdles to overcome before the tool can be truly helpful.

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

Prices may be subject to local taxes which are calculated during checkout

Nature 619 , 443-444 (2023)

doi: https://doi.org/10.1038/d41586-023-02218-z

Updates & Corrections

Correction 11 July 2023 : An earlier version of this story implied that human researchers had guided ChatGPT through the steps to create a research paper. In fact, the data-to-paper tool developed by Kishony and Ifargan acted as an intermediary between ChatGPT and the researchers. The text has been corrected in several places to reflect this.

Reprints and permissions

Who will make AlphaFold3 open source? Scientists race to crack AI model

News 23 MAY 24

Egypt is building a $1-billion mega-museum. Will it bring Egyptology home?

News Feature 22 MAY 24

Pay researchers to spot errors in published papers

World View 21 MAY 24

Illuminating ‘the ugly side of science’: fresh incentives for reporting negative results

Career Feature 08 MAY 24

Plagiarism in peer-review reports could be the ‘tip of the iceberg’

Nature Index 01 MAY 24

Algorithm ranks peer reviewers by reputation — but critics warn of bias

Nature Index 25 APR 24

Postdoctoral Associate - Amyloid Strain Differences in Alzheimer's Disease

Houston, Texas (US)

Baylor College of Medicine (BCM)

Postdoctoral Associate- Bioinformatics of Alzheimer's disease

Postdoctoral associate- alzheimer's gene therapy, postdoctoral associate, kaust global postdoctoral fellowship.

The KAUST Global Fellowship Program is designed to attract emerging research leaders working across areas under the four research priorities of KAUST.

Saudi Arabia (SA)

King Abdullah University of Science and Technology (KAUST

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Genuine software, legally FREE - no cracking required!

Edit Word, Excel, and PPT effortlessly

Read, edit, and convert PDFs with the powerful PDF toolkit.

Microsoft-like interface, easy to use.

Windows • MacOS • Linux • iOS • Android

• Articles of Office solution

Step-by-step Guide to Using ChatGPT to Write a Report, Thesis and Dissertation

You must have heard or read about ChatGPT. What is it? A software or a magician? ChatGPT is an artificial intelligence chatbot developed and launched by OpenAI in November 2022. This chatbot can write answers, reports, codes, prompts, and more in seconds.

Moreover, it can write computer programs, compose music, teleplays, fairy tales, and write poetry and songs. It’s built with OpenAI’s GPT 3.5 and 4 families of large language models. The latest version of ChatGPT, released on 14th March 2023, is built on GPT 4 OpenAI model and can be purchased through a subscription for a specific time.

Benefits of using ChatGPT to write reports, theses, and dissertations

ChatGPT is a powerful artificial intelligence (AI) chatbot with many benefits. Today we shall be highlighting the benefits ChatGPT has on reports, theses, and dissertations.

Reports are professional documents submitted to an institute, department, company, and more. They are formal documents containing a written account of something observed or investigated. Below are some benefits of using ChatGPT to write reports.

Saves time:  ChatGPT saves your precious time; it writes your reports quickly and saves the time you would have spent researching and writing from the beginning.

Quality content:  The AI chatbot has been trained with massive data; hence it can write high-quality reports for you.

Variety of Styles:  Reports are usually long; thus, they can bore the reader if the content is not engaging. ChatGPT uses different styles, i.e., bullet points, lists, paragraphs, and more. This makes a report engaging.

Consistency and Productivity:  ChatGPT write the report in a consistent style and tone. This improves the readability of the report. Moreover, as ChatGPT saves your precious time, you can spend that time focusing on other tasks, improving your productivity.

Theses is a theory or personal research document. These are mainly written by university students proposing research papers on particular topics. Below are the benefits of using ChatGPT to write theses.

New idea:  ChatGPT helps you by providing a variety of ideas that can help you write your thesis. Moreover, the ideas can make your thesis stand out from others.

Guidance:  ChatGPT guides you throughout your thesis writing by providing references, and research material, summarising long research essays, and highlighting important points.

Writing Guidance:  The artificial intelligence model can advise and guide your style, tone, grammar, and more. ChatGPT guides you with this writing; further, it can proofread and rephrase your content.

3. Dissertation

Dissertation is a formal essay on a particular topic. It’s the same as the thesis and is mainly written and submitted by university students. Below are the advantages of using ChatGPT for writing a dissertation.

Knowledge:  ChatGPT is trained with vast knowledge and provides dissertation writers access to knowledge. The more diverse knowledge, the better dissertation.

Saves Time:  Dissertation writing is time-consuming; however, ChatGPT can generate texts for you instantly. You can ask ChatGPT to write sections, paragraphs, and particular dissertation headings. Moreover, it can proofread and check your dissertation's grammar, style, and errors.

Assistance with writing:  Dissertation requires a lot of time and effort. Moreover, quality is an essential factor you should keep in mind while writing a dissertation; chatGPT suggests ways to improve your dissertation writing. Moreover, ChatGPT can proofread, rephrase and highlight writing errors for you.

Step-by-Step Guide: Create a ChatGPT Account

Using ChatGPT might be complex; thus, we are here to help you. Below are steps to create an account and write reports and theses or dissertations.

1. Setting Up ChatGPT

Now that you know ChatGPT and its benefits associated with reports, theses, and dissertation writing, it’s time to set up a ChatGPT account.

The first thing to do is to visit the official website of OpenAI’s artificial intelligence chatbot ChatGPT.

After successfully landing on the official website of ChatGPT, you’ll see a login and sign-up option. You need to login in using your login credentials and progress further. However, if you do not have an account, click sign up, add an email, and create a password. Moreover, you’ll need to add your personal data, i.e., your date of birth, and verify your mobile number.

Afterward, you need to log in with the same email and password. OpenAI allows people to log in through Microsoft and Google accounts. If you have a valid Microsoft or Google account, simply click on login, click on Microsoft or Google, and log in to the selected account. Verify your phone number, and you’ll successfully log in to OpenAI to use ChatGPT.

After successfully logging in to OpenAI, you can start a new chat or use previous ones (if you logged in before and used chatbot). Click the new chat button on the left and start using the chatGPT. You can ask questions, gain knowledge, ask to proofread your work, suggest edits, and do more instantly.

If you are in a country where the use of ChatGPT is not allowed and you wish to register an account, you can refer to my other article " How to use Chatgpt ". It provides a detailed tutorial on how to register an account in such countries.

How to use ChatGPT to write a report

Setting up the ChatGPT account is easier than using it. Below we’ll guide you thoroughly on how to write a report using ChatGPT.

Setting up the Parameters

The first thing you must do is set parameters. What are the parameters? Parameters are framework or structure. You need to set up the report's parameters as they help control the report’s content and use other reports’ material in arguments. You need to tell ChatGPT where to start and let it know the limits of your report. In short, you need to provide ChatGPT with a structure under which it should generate your report.

Creating an Outline

Create an outline for your report. The outline may start with an introduction, having headings, bullet points, paragraphs, and more. You must provide an accurate outline to enable ChatGPT to write your report. This ensures that your report covers all the aspects in a good flow and all the required information. Without an outline, chatGPT may be unable to write it in a flow or may write something unnecessary for your report.

Writing the Report

The last thing is to ask ChatGPT to write the report for you. You need to set parameters, provide an outline, write a good prompt, and wait for ChatGPT to generate the report for you for a minute or two.

Topic: Impact of remote work on employee productivity

Purpose: To understand and examine the impact of remote work on the productivity of employees with findings and recommendations.

How to use ChatGPT to write a thesis or dissertation

As writing theses or dissertations is complex and requires time and energy, many people want to learn to use chatGPT to write them. Here’s how to write a thesis using Chatgpt.

Choosing a topic

After logging in to your OpenAI account, click on the new chat and choose a topic you want ChatGPT to write a thesis or dissertation on. This can be any topic that a normal human being can think of.

After deciding on a thesis or dissertation topic, you must create an outline. Creating an outline has its own benefits, as your theses will cover all aspects and topics in a flow, and the knowledge in the theses will be organized.

Writing the Thesis

Now that you have decided on a topic and created an outline, the next thing to do is write the thesis. Writing a good prompt will result in a good thesis. After writing a prompt for the thesis, click on the save and submit button, and wait a few minutes before ChatGPT can complete generating the thesis for you.

Topic: ChatGPT and its importance in conversational AI applications.

Purpose: To access and understand ChatGPT, its importance, benefits, and uses. Moreover, to examine its importance in conversational AI applications.

Now, you can use AI to assist you in generating a thesis, but it's important to note that you still need to carefully review the content generated by the AI to avoid any fabrication. Additionally, there are some universities that currently do not allow AI-generated theses. These universities may employ AI detection tools to check if a thesis was written by AI. In such cases, you can try using a paraphrasing tool to rewrite the AI-generated content until it passes the detection:

Recommended AI detection tools:  GPT-2 Output Detector

Recommended paraphrasing tools:  Quillbot

Perform another round of detection

Other AI or productivity tools recommended

There are various other AI or productivity tools that you can use instead of ChatGPT. Below are some.

1.  MidJourney

MidJourney is an artificial intelligence program that Mid Journey, Inc created and launched. The AI program can generate images and art using the prompts. You can use MidJourney for 20 free jobs to create or generate images for you on prompts. This software can help you create amazing images for your report and thesis. A thesis or report would look boring without images that engage the audience; hence you can use MidJourney AI to generate images for your thesis or report.

2.  WPS Office

WPS Office is a free office software that allows users to use Word, Excel, PPT, and PDF documents under a single roof. It’s free software that promotes creativity and boosts the productivity of users. The software has more than 500 million active users worldwide. The software lets users view, edit, translate, annotate, print, and do more. It’s compatible with Windows, MacOS, IOS, and Android.

Moreover, it’s free and has various advanced features and functions. The software enables users to write reports and a thesis using diverse tools. You can add bullet points, comments, and suggestions, highlight texts, and translate sentences and words. This is the best software for writing a report or dissertation, as it has templates for the report and thesis that can help you.

3. Chinchilla AI

Developed and launched by DeepMind in March 2022, this AI language model can better write your reports and thesis, requiring less computer power for interference and fine-tuning. The Chinchilla AI is said to outperform a number of traditional language models in terms of accuracy; hence, it can generate better and more accurate reports and a thesis for you. However, the software is currently in the testing phase and cannot be accessed by the general public.

A. Can I write a thesis with ChatGPT?

Yes. You can use ChatGPT to write a thesis. Start with choosing a topic, creating an outline, and writing a prompt to enable ChatGPT to generate a thesis on the topic for you.

B. Can I write a report with ChatGPT?

Yes. Writing a report using ChatGPT is possible and easy. All you need to do is set the report's parameters, create an outline, and submit a prompt to enable ChatGPT to generate the report.

C. How do you use ChatGPT to improve your writing?

ChatGPT can improve your writing by suggesting edits, proofreading, and suggesting new ideas. Moreover, ChatGPT can highlight errors too.

D. Can ChatGPT rewrite paragraphs?

Yes. ChatGPT is a powerful tool that can rewrite your texts better and make them more engaging and readable.

ChatGPT is a powerful artificial intelligence model that can help users with numerous tasks. So far, we have learned about ChatGPT and its benefits associated with report, thesis, or dissertation writing. Moreover, we learned how to write a thesis and report using ChatGPT. Setting up and using ChatGPT to write reports and thesis. The article also highlighted the best alternatives to ChatGPT for writing reports and thesis; one of them is  WPS Office .

• 1. Top 10 Best Business Report Chatgpt Prompt Example 2024
• 2. How to Use WPS AI/Chatgpt to Write Research Papers: Guide for Beginners
• 3. How to Use WPS AI and ChatGPT to Analyze PDF Report
• 4. How to Use WPS AI/Chatgpt to Write Essays: Guide for Beginners
• 5. Ultimate Guide to Write A Seminar PDF Report
• 6. How to Use Wps AI/Chatgpt to Write Technical Document: Guide for Beginners

15 years of office industry experience, tech lover and copywriter. Follow me for product reviews, comparisons, and recommendations for new apps and software.

A systematic literature review of empirical research on ChatGPT in education

• Open access
• Published: 26 May 2024
• Volume 3 , article number  60 , ( 2024 )

Cite this article

You have full access to this open access article

• Yazid Albadarin   ORCID: orcid.org/0009-0005-8068-8902 1 ,
• Mohammed Saqr 1 ,
• Nicolas Pope 1 &
• Markku Tukiainen 1  

166 Accesses

Explore all metrics

Over the last four decades, studies have investigated the incorporation of Artificial Intelligence (AI) into education. A recent prominent AI-powered technology that has impacted the education sector is ChatGPT. This article provides a systematic review of 14 empirical studies incorporating ChatGPT into various educational settings, published in 2022 and before the 10th of April 2023—the date of conducting the search process. It carefully followed the essential steps outlined in the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines, as well as Okoli’s (Okoli in Commun Assoc Inf Syst, 2015) steps for conducting a rigorous and transparent systematic review. In this review, we aimed to explore how students and teachers have utilized ChatGPT in various educational settings, as well as the primary findings of those studies. By employing Creswell’s (Creswell in Educational research: planning, conducting, and evaluating quantitative and qualitative research [Ebook], Pearson Education, London, 2015) coding techniques for data extraction and interpretation, we sought to gain insight into their initial attempts at ChatGPT incorporation into education. This approach also enabled us to extract insights and considerations that can facilitate its effective and responsible use in future educational contexts. The results of this review show that learners have utilized ChatGPT as a virtual intelligent assistant, where it offered instant feedback, on-demand answers, and explanations of complex topics. Additionally, learners have used it to enhance their writing and language skills by generating ideas, composing essays, summarizing, translating, paraphrasing texts, or checking grammar. Moreover, learners turned to it as an aiding tool to facilitate their directed and personalized learning by assisting in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks. However, the results of specific studies (n = 3, 21.4%) show that overuse of ChatGPT may negatively impact innovative capacities and collaborative learning competencies among learners. Educators, on the other hand, have utilized ChatGPT to create lesson plans, generate quizzes, and provide additional resources, which helped them enhance their productivity and efficiency and promote different teaching methodologies. Despite these benefits, the majority of the reviewed studies recommend the importance of conducting structured training, support, and clear guidelines for both learners and educators to mitigate the drawbacks. This includes developing critical evaluation skills to assess the accuracy and relevance of information provided by ChatGPT, as well as strategies for integrating human interaction and collaboration into learning activities that involve AI tools. Furthermore, they also recommend ongoing research and proactive dialogue with policymakers, stakeholders, and educational practitioners to refine and enhance the use of AI in learning environments. This review could serve as an insightful resource for practitioners who seek to integrate ChatGPT into education and stimulate further research in the field.

Similar content being viewed by others

Empowering learners with ChatGPT: insights from a systematic literature exploration

Incorporating AI in foreign language education: An investigation into ChatGPT’s effect on foreign language learners

Large language models in education: A focus on the complementary relationship between human teachers and ChatGPT

Avoid common mistakes on your manuscript.

1 Introduction

Educational technology, a rapidly evolving field, plays a crucial role in reshaping the landscape of teaching and learning [ 82 ]. One of the most transformative technological innovations of our era that has influenced the field of education is Artificial Intelligence (AI) [ 50 ]. Over the last four decades, AI in education (AIEd) has gained remarkable attention for its potential to make significant advancements in learning, instructional methods, and administrative tasks within educational settings [ 11 ]. In particular, a large language model (LLM), a type of AI algorithm that applies artificial neural networks (ANNs) and uses massively large data sets to understand, summarize, generate, and predict new content that is almost difficult to differentiate from human creations [ 79 ], has opened up novel possibilities for enhancing various aspects of education, from content creation to personalized instruction [ 35 ]. Chatbots that leverage the capabilities of LLMs to understand and generate human-like responses have also presented the capacity to enhance student learning and educational outcomes by engaging students, offering timely support, and fostering interactive learning experiences [ 46 ].

The ongoing and remarkable technological advancements in chatbots have made their use more convenient, increasingly natural and effortless, and have expanded their potential for deployment across various domains [ 70 ]. One prominent example of chatbot applications is the Chat Generative Pre-Trained Transformer, known as ChatGPT, which was introduced by OpenAI, a leading AI research lab, on November 30th, 2022. ChatGPT employs a variety of deep learning techniques to generate human-like text, with a particular focus on recurrent neural networks (RNNs). Long short-term memory (LSTM) allows it to grasp the context of the text being processed and retain information from previous inputs. Also, the transformer architecture, a neural network architecture based on the self-attention mechanism, allows it to analyze specific parts of the input, thereby enabling it to produce more natural-sounding and coherent output. Additionally, the unsupervised generative pre-training and the fine-tuning methods allow ChatGPT to generate more relevant and accurate text for specific tasks [ 31 , 62 ]. Furthermore, reinforcement learning from human feedback (RLHF), a machine learning approach that combines reinforcement learning techniques with human-provided feedback, has helped improve ChatGPT’s model by accelerating the learning process and making it significantly more efficient.

This cutting-edge natural language processing (NLP) tool is widely recognized as one of today's most advanced LLMs-based chatbots [ 70 ], allowing users to ask questions and receive detailed, coherent, systematic, personalized, convincing, and informative human-like responses [ 55 ], even within complex and ambiguous contexts [ 63 , 77 ]. ChatGPT is considered the fastest-growing technology in history: in just three months following its public launch, it amassed an estimated 120 million monthly active users [ 16 ] with an estimated 13 million daily queries [ 49 ], surpassing all other applications [ 64 ]. This remarkable growth can be attributed to the unique features and user-friendly interface that ChatGPT offers. Its intuitive design allows users to interact seamlessly with the technology, making it accessible to a diverse range of individuals, regardless of their technical expertise [ 78 ]. Additionally, its exceptional performance results from a combination of advanced algorithms, continuous enhancements, and extensive training on a diverse dataset that includes various text sources such as books, articles, websites, and online forums [ 63 ], have contributed to a more engaging and satisfying user experience [ 62 ]. These factors collectively explain its remarkable global growth and set it apart from predecessors like Bard, Bing Chat, ERNIE, and others.

In this context, several studies have explored the technological advancements of chatbots. One noteworthy recent research effort, conducted by Schöbel et al. [ 70 ], stands out for its comprehensive analysis of more than 5,000 studies on communication agents. This study offered a comprehensive overview of the historical progression and future prospects of communication agents, including ChatGPT. Moreover, other studies have focused on making comparisons, particularly between ChatGPT and alternative chatbots like Bard, Bing Chat, ERNIE, LaMDA, BlenderBot, and various others. For example, O’Leary [ 53 ] compared two chatbots, LaMDA and BlenderBot, with ChatGPT and revealed that ChatGPT outperformed both. This superiority arises from ChatGPT’s capacity to handle a wider range of questions and generate slightly varied perspectives within specific contexts. Similarly, ChatGPT exhibited an impressive ability to formulate interpretable responses that were easily understood when compared with Google's feature snippet [ 34 ]. Additionally, ChatGPT was compared to other LLMs-based chatbots, including Bard and BERT, as well as ERNIE. The findings indicated that ChatGPT exhibited strong performance in the given tasks, often outperforming the other models [ 59 ].

Furthermore, in the education context, a comprehensive study systematically compared a range of the most promising chatbots, including Bard, Bing Chat, ChatGPT, and Ernie across a multidisciplinary test that required higher-order thinking. The study revealed that ChatGPT achieved the highest score, surpassing Bing Chat and Bard [ 64 ]. Similarly, a comparative analysis was conducted to compare ChatGPT with Bard in answering a set of 30 mathematical questions and logic problems, grouped into two question sets. Set (A) is unavailable online, while Set (B) is available online. The results revealed ChatGPT's superiority in Set (A) over Bard. Nevertheless, Bard's advantage emerged in Set (B) due to its capacity to access the internet directly and retrieve answers, a capability that ChatGPT does not possess [ 57 ]. However, through these varied assessments, ChatGPT consistently highlights its exceptional prowess compared to various alternatives in the ever-evolving chatbot technology.

The widespread adoption of chatbots, especially ChatGPT, by millions of students and educators, has sparked extensive discussions regarding its incorporation into the education sector [ 64 ]. Accordingly, many scholars have contributed to the discourse, expressing both optimism and pessimism regarding the incorporation of ChatGPT into education. For example, ChatGPT has been highlighted for its capabilities in enriching the learning and teaching experience through its ability to support different learning approaches, including adaptive learning, personalized learning, and self-directed learning [ 58 , 60 , 91 ]), deliver summative and formative feedback to students and provide real-time responses to questions, increase the accessibility of information [ 22 , 40 , 43 ], foster students’ performance, engagement and motivation [ 14 , 44 , 58 ], and enhance teaching practices [ 17 , 18 , 64 , 74 ].

On the other hand, concerns have been also raised regarding its potential negative effects on learning and teaching. These include the dissemination of false information and references [ 12 , 23 , 61 , 85 ], biased reinforcement [ 47 , 50 ], compromised academic integrity [ 18 , 40 , 66 , 74 ], and the potential decline in students' skills [ 43 , 61 , 64 , 74 ]. As a result, ChatGPT has been banned in multiple countries, including Russia, China, Venezuela, Belarus, and Iran, as well as in various educational institutions in India, Italy, Western Australia, France, and the United States [ 52 , 90 ].

Clearly, the advent of chatbots, especially ChatGPT, has provoked significant controversy due to their potential impact on learning and teaching. This indicates the necessity for further exploration to gain a deeper understanding of this technology and carefully evaluate its potential benefits, limitations, challenges, and threats to education [ 79 ]. Therefore, conducting a systematic literature review will provide valuable insights into the potential prospects and obstacles linked to its incorporation into education. This systematic literature review will primarily focus on ChatGPT, driven by the aforementioned key factors outlined above.

However, the existing literature lacks a systematic literature review of empirical studies. Thus, this systematic literature review aims to address this gap by synthesizing the existing empirical studies conducted on chatbots, particularly ChatGPT, in the field of education, highlighting how ChatGPT has been utilized in educational settings, and identifying any existing gaps. This review may be particularly useful for researchers in the field and educators who are contemplating the integration of ChatGPT or any chatbot into education. The following research questions will guide this study:

What are students' and teachers' initial attempts at utilizing ChatGPT in education?

What are the main findings derived from empirical studies that have incorporated ChatGPT into learning and teaching?

2 Methodology

To conduct this study, the authors followed the essential steps of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) and Okoli’s [ 54 ] steps for conducting a systematic review. These included identifying the study’s purpose, drafting a protocol, applying a practical screening process, searching the literature, extracting relevant data, evaluating the quality of the included studies, synthesizing the studies, and ultimately writing the review. The subsequent section provides an extensive explanation of how these steps were carried out in this study.

2.1 Identify the purpose

Given the widespread adoption of ChatGPT by students and teachers for various educational purposes, often without a thorough understanding of responsible and effective use or a clear recognition of its potential impact on learning and teaching, the authors recognized the need for further exploration of ChatGPT's impact on education in this early stage. Therefore, they have chosen to conduct a systematic literature review of existing empirical studies that incorporate ChatGPT into educational settings. Despite the limited number of empirical studies due to the novelty of the topic, their goal is to gain a deeper understanding of this technology and proactively evaluate its potential benefits, limitations, challenges, and threats to education. This effort could help to understand initial reactions and attempts at incorporating ChatGPT into education and bring out insights and considerations that can inform the future development of education.

2.2 Draft the protocol

The next step is formulating the protocol. This protocol serves to outline the study process in a rigorous and transparent manner, mitigating researcher bias in study selection and data extraction [ 88 ]. The protocol will include the following steps: generating the research question, predefining a literature search strategy, identifying search locations, establishing selection criteria, assessing the studies, developing a data extraction strategy, and creating a timeline.

2.3 Apply practical screen

The screening step aims to accurately filter the articles resulting from the searching step and select the empirical studies that have incorporated ChatGPT into educational contexts, which will guide us in answering the research questions and achieving the objectives of this study. To ensure the rigorous execution of this step, our inclusion and exclusion criteria were determined based on the authors' experience and informed by previous successful systematic reviews [ 21 ]. Table 1 summarizes the inclusion and exclusion criteria for study selection.

2.4 Literature search

We conducted a thorough literature search to identify articles that explored, examined, and addressed the use of ChatGPT in Educational contexts. We utilized two research databases: Dimensions.ai, which provides access to a large number of research publications, and lens.org, which offers access to over 300 million articles, patents, and other research outputs from diverse sources. Additionally, we included three databases, Scopus, Web of Knowledge, and ERIC, which contain relevant research on the topic that addresses our research questions. To browse and identify relevant articles, we used the following search formula: ("ChatGPT" AND "Education"), which included the Boolean operator "AND" to get more specific results. The subject area in the Scopus and ERIC databases were narrowed to "ChatGPT" and "Education" keywords, and in the WoS database was limited to the "Education" category. The search was conducted between the 3rd and 10th of April 2023, which resulted in 276 articles from all selected databases (111 articles from Dimensions.ai, 65 from Scopus, 28 from Web of Science, 14 from ERIC, and 58 from Lens.org). These articles were imported into the Rayyan web-based system for analysis. The duplicates were identified automatically by the system. Subsequently, the first author manually reviewed the duplicated articles ensured that they had the same content, and then removed them, leaving us with 135 unique articles. Afterward, the titles, abstracts, and keywords of the first 40 manuscripts were scanned and reviewed by the first author and were discussed with the second and third authors to resolve any disagreements. Subsequently, the first author proceeded with the filtering process for all articles and carefully applied the inclusion and exclusion criteria as presented in Table  1 . Articles that met any one of the exclusion criteria were eliminated, resulting in 26 articles. Afterward, the authors met to carefully scan and discuss them. The authors agreed to eliminate any empirical studies solely focused on checking ChatGPT capabilities, as these studies do not guide us in addressing the research questions and achieving the study's objectives. This resulted in 14 articles eligible for analysis.

2.5 Quality appraisal

The examination and evaluation of the quality of the extracted articles is a vital step [ 9 ]. Therefore, the extracted articles were carefully evaluated for quality using Fink’s [ 24 ] standards, which emphasize the necessity for detailed descriptions of methodology, results, conclusions, strengths, and limitations. The process began with a thorough assessment of each study's design, data collection, and analysis methods to ensure their appropriateness and comprehensive execution. The clarity, consistency, and logical progression from data to results and conclusions were also critically examined. Potential biases and recognized limitations within the studies were also scrutinized. Ultimately, two articles were excluded for failing to meet Fink’s criteria, particularly in providing sufficient detail on methodology, results, conclusions, strengths, or limitations. The review process is illustrated in Fig.  1 .

The study selection process

2.6 Data extraction

The next step is data extraction, the process of capturing the key information and categories from the included studies. To improve efficiency, reduce variation among authors, and minimize errors in data analysis, the coding categories were constructed using Creswell's [ 15 ] coding techniques for data extraction and interpretation. The coding process involves three sequential steps. The initial stage encompasses open coding , where the researcher examines the data, generates codes to describe and categorize it, and gains a deeper understanding without preconceived ideas. Following open coding is axial coding , where the interrelationships between codes from open coding are analyzed to establish more comprehensive categories or themes. The process concludes with selective coding , refining and integrating categories or themes to identify core concepts emerging from the data. The first coder performed the coding process, then engaged in discussions with the second and third authors to finalize the coding categories for the first five articles. The first coder then proceeded to code all studies and engaged again in discussions with the other authors to ensure the finalization of the coding process. After a comprehensive analysis and capturing of the key information from the included studies, the data extraction and interpretation process yielded several themes. These themes have been categorized and are presented in Table  2 . It is important to note that open coding results were removed from Table  2 for aesthetic reasons, as it included many generic aspects, such as words, short phrases, or sentences mentioned in the studies.

2.7 Synthesize studies

In this stage, we will gather, discuss, and analyze the key findings that emerged from the selected studies. The synthesis stage is considered a transition from an author-centric to a concept-centric focus, enabling us to map all the provided information to achieve the most effective evaluation of the data [ 87 ]. Initially, the authors extracted data that included general information about the selected studies, including the author(s)' names, study titles, years of publication, educational levels, research methodologies, sample sizes, participants, main aims or objectives, raw data sources, and analysis methods. Following that, all key information and significant results from the selected studies were compiled using Creswell’s [ 15 ] coding techniques for data extraction and interpretation to identify core concepts and themes emerging from the data, focusing on those that directly contributed to our research questions and objectives, such as the initial utilization of ChatGPT in learning and teaching, learners' and educators' familiarity with ChatGPT, and the main findings of each study. Finally, the data related to each selected study were extracted into an Excel spreadsheet for data processing. The Excel spreadsheet was reviewed by the authors, including a series of discussions to ensure the finalization of this process and prepare it for further analysis. Afterward, the final result being analyzed and presented in various types of charts and graphs. Table 4 presents the extracted data from the selected studies, with each study labeled with a capital 'S' followed by a number.

This section consists of two main parts. The first part provides a descriptive analysis of the data compiled from the reviewed studies. The second part presents the answers to the research questions and the main findings of these studies.

3.1 Part 1: descriptive analysis

This section will provide a descriptive analysis of the reviewed studies, including educational levels and fields, participants distribution, country contribution, research methodologies, study sample size, study population, publication year, list of journals, familiarity with ChatGPT, source of data, and the main aims and objectives of the studies. Table 4 presents a comprehensive overview of the extracted data from the selected studies.

3.1.1 The number of the reviewed studies and publication years

The total number of the reviewed studies was 14. All studies were empirical studies and published in different journals focusing on Education and Technology. One study was published in 2022 [S1], while the remaining were published in 2023 [S2]-[S14]. Table 3 illustrates the year of publication, the names of the journals, and the number of reviewed studies published in each journal for the studies reviewed.

3.1.2 Educational levels and fields

The majority of the reviewed studies, 11 studies, were conducted in higher education institutions [S1]-[S10] and [S13]. Two studies did not specify the educational level of the population [S12] and [S14], while one study focused on elementary education [S11]. However, the reviewed studies covered various fields of education. Three studies focused on Arts and Humanities Education [S8], [S11], and [S14], specifically English Education. Two studies focused on Engineering Education, with one in Computer Engineering [S2] and the other in Construction Education [S3]. Two studies focused on Mathematics Education [S5] and [S12]. One study focused on Social Science Education [S13]. One study focused on Early Education [S4]. One study focused on Journalism Education [S9]. Finally, three studies did not specify the field of education [S1], [S6], and [S7]. Figure  2 represents the educational levels in the reviewed studies, while Fig.  3 represents the context of the reviewed studies.

Educational levels in the reviewed studies

Context of the reviewed studies

3.1.3 Participants distribution and countries contribution

The reviewed studies have been conducted across different geographic regions, providing a diverse representation of the studies. The majority of the studies, 10 in total, [S1]-[S3], [S5]-[S9], [S11], and [S14], primarily focused on participants from single countries such as Pakistan, the United Arab Emirates, China, Indonesia, Poland, Saudi Arabia, South Korea, Spain, Tajikistan, and the United States. In contrast, four studies, [S4], [S10], [S12], and [S13], involved participants from multiple countries, including China and the United States [S4], China, the United Kingdom, and the United States [S10], the United Arab Emirates, Oman, Saudi Arabia, and Jordan [S12], Turkey, Sweden, Canada, and Australia [ 13 ]. Figures  4 and 5 illustrate the distribution of participants, whether from single or multiple countries, and the contribution of each country in the reviewed studies, respectively.

The reviewed studies conducted in single or multiple countries

The Contribution of each country in the studies

3.1.4 Study population and sample size

Four study populations were included: university students, university teachers, university teachers and students, and elementary school teachers. Six studies involved university students [S2], [S3], [S5] and [S6]-[S8]. Three studies focused on university teachers [S1], [S4], and [S6], while one study specifically targeted elementary school teachers [S11]. Additionally, four studies included both university teachers and students [S10] and [ 12 , 13 , 14 ], and among them, study [S13] specifically included postgraduate students. In terms of the sample size of the reviewed studies, nine studies included a small sample size of less than 50 participants [S1], [S3], [S6], [S8], and [S10]-[S13]. Three studies had 50–100 participants [S2], [S9], and [S14]. Only one study had more than 100 participants [S7]. It is worth mentioning that study [S4] adopted a mixed methods approach, including 10 participants for qualitative analysis and 110 participants for quantitative analysis.

3.1.5 Participants’ familiarity with using ChatGPT

The reviewed studies recruited a diverse range of participants with varying levels of familiarity with ChatGPT. Five studies [S2], [S4], [S6], [S8], and [S12] involved participants already familiar with ChatGPT, while eight studies [S1], [S3], [S5], [S7], [S9], [S10], [S13] and [S14] included individuals with differing levels of familiarity. Notably, one study [S11] had participants who were entirely unfamiliar with ChatGPT. It is important to note that four studies [S3], [S5], [S9], and [S11] provided training or guidance to their participants before conducting their studies, while ten studies [S1], [S2], [S4], [S6]-[S8], [S10], and [S12]-[S14] did not provide training due to the participants' existing familiarity with ChatGPT.

3.1.6 Research methodology approaches and source(S) of data

The reviewed studies adopted various research methodology approaches. Seven studies adopted qualitative research methodology [S1], [S4], [S6], [S8], [S10], [S11], and [S12], while three studies adopted quantitative research methodology [S3], [S7], and [S14], and four studies employed mixed-methods, which involved a combination of both the strengths of qualitative and quantitative methods [S2], [S5], [S9], and [S13].

In terms of the source(s) of data, the reviewed studies obtained their data from various sources, such as interviews, questionnaires, and pre-and post-tests. Six studies relied on interviews as their primary source of data collection [S1], [S4], [S6], [S10], [S11], and [S12], four studies relied on questionnaires [S2], [S7], [S13], and [S14], two studies combined the use of pre-and post-tests and questionnaires for data collection [S3] and [S9], while two studies combined the use of questionnaires and interviews to obtain the data [S5] and [S8]. It is important to note that six of the reviewed studies were quasi-experimental [S3], [S5], [S8], [S9], [S12], and [S14], while the remaining ones were experimental studies [S1], [S2], [S4], [S6], [S7], [S10], [S11], and [S13]. Figures  6 and 7 illustrate the research methodologies and the source (s) of data used in the reviewed studies, respectively.

Research methodologies in the reviewed studies

Source of data in the reviewed studies

3.1.7 The aim and objectives of the studies

The reviewed studies encompassed a diverse set of aims, with several of them incorporating multiple primary objectives. Six studies [S3], [S6], [S7], [S8], [S11], and [S12] examined the integration of ChatGPT in educational contexts, and four studies [S4], [S5], [S13], and [S14] investigated the various implications of its use in education, while three studies [S2], [S9], and [S10] aimed to explore both its integration and implications in education. Additionally, seven studies explicitly explored attitudes and perceptions of students [S2] and [S3], educators [S1] and [S6], or both [S10], [S12], and [S13] regarding the utilization of ChatGPT in educational settings.

3.2 Part 2: research questions and main findings of the reviewed studies

This part will present the answers to the research questions and the main findings of the reviewed studies, classified into two main categories (learning and teaching) according to AI Education classification by [ 36 ]. Figure  8 summarizes the main findings of the reviewed studies in a visually informative diagram. Table 4 provides a detailed list of the key information extracted from the selected studies that led to generating these themes.

The main findings in the reviewed studies

4 Students' initial attempts at utilizing ChatGPT in learning and main findings from students' perspective

4.1 virtual intelligent assistant.

Nine studies demonstrated that ChatGPT has been utilized by students as an intelligent assistant to enhance and support their learning. Students employed it for various purposes, such as answering on-demand questions [S2]-[S5], [S8], [S10], and [S12], providing valuable information and learning resources [S2]-[S5], [S6], and [S8], as well as receiving immediate feedback [S2], [S4], [S9], [S10], and [S12]. In this regard, students generally were confident in the accuracy of ChatGPT's responses, considering them relevant, reliable, and detailed [S3], [S4], [S5], and [S8]. However, some students indicated the need for improvement, as they found that answers are not always accurate [S2], and that misleading information may have been provided or that it may not always align with their expectations [S6] and [S10]. It was also observed by the students that the accuracy of ChatGPT is dependent on several factors, including the quality and specificity of the user's input, the complexity of the question or topic, and the scope and relevance of its training data [S12]. Many students felt that ChatGPT's answers were not always accurate and most of them believed that it requires good background knowledge to work with.

4.2 Writing and language proficiency assistant

Six of the reviewed studies highlighted that ChatGPT has been utilized by students as a valuable assistant tool to improve their academic writing skills and language proficiency. Among these studies, three mainly focused on English education, demonstrating that students showed sufficient mastery in using ChatGPT for generating ideas, summarizing, paraphrasing texts, and completing writing essays [S8], [S11], and [S14]. Furthermore, ChatGPT helped them in writing by making students active investigators rather than passive knowledge recipients and facilitated the development of their writing skills [S11] and [S14]. Similarly, ChatGPT allowed students to generate unique ideas and perspectives, leading to deeper analysis and reflection on their journalism writing [S9]. In terms of language proficiency, ChatGPT allowed participants to translate content into their home languages, making it more accessible and relevant to their context [S4]. It also enabled them to request changes in linguistic tones or flavors [S8]. Moreover, participants used it to check grammar or as a dictionary [S11].

4.3 Valuable resource for learning approaches

Five studies demonstrated that students used ChatGPT as a valuable complementary resource for self-directed learning. It provided learning resources and guidance on diverse educational topics and created a supportive home learning environment [S2] and [S4]. Moreover, it offered step-by-step guidance to grasp concepts at their own pace and enhance their understanding [S5], streamlined task and project completion carried out independently [S7], provided comprehensive and easy-to-understand explanations on various subjects [S10], and assisted in studying geometry operations, thereby empowering them to explore geometry operations at their own pace [S12]. Three studies showed that students used ChatGPT as a valuable learning resource for personalized learning. It delivered age-appropriate conversations and tailored teaching based on a child's interests [S4], acted as a personalized learning assistant, adapted to their needs and pace, which assisted them in understanding mathematical concepts [S12], and enabled personalized learning experiences in social sciences by adapting to students' needs and learning styles [S13]. On the other hand, it is important to note that, according to one study [S5], students suggested that using ChatGPT may negatively affect collaborative learning competencies between students.

4.4 Enhancing students' competencies

Six of the reviewed studies have shown that ChatGPT is a valuable tool for improving a wide range of skills among students. Two studies have provided evidence that ChatGPT led to improvements in students' critical thinking, reasoning skills, and hazard recognition competencies through engaging them in interactive conversations or activities and providing responses related to their disciplines in journalism [S5] and construction education [S9]. Furthermore, two studies focused on mathematical education have shown the positive impact of ChatGPT on students' problem-solving abilities in unraveling problem-solving questions [S12] and enhancing the students' understanding of the problem-solving process [S5]. Lastly, one study indicated that ChatGPT effectively contributed to the enhancement of conversational social skills [S4].

4.5 Supporting students' academic success

Seven of the reviewed studies highlighted that students found ChatGPT to be beneficial for learning as it enhanced learning efficiency and improved the learning experience. It has been observed to improve students' efficiency in computer engineering studies by providing well-structured responses and good explanations [S2]. Additionally, students found it extremely useful for hazard reporting [S3], and it also enhanced their efficiency in solving mathematics problems and capabilities [S5] and [S12]. Furthermore, by finding information, generating ideas, translating texts, and providing alternative questions, ChatGPT aided students in deepening their understanding of various subjects [S6]. It contributed to an increase in students' overall productivity [S7] and improved efficiency in composing written tasks [S8]. Regarding learning experiences, ChatGPT was instrumental in assisting students in identifying hazards that they might have otherwise overlooked [S3]. It also improved students' learning experiences in solving mathematics problems and developing abilities [S5] and [S12]. Moreover, it increased students' successful completion of important tasks in their studies [S7], particularly those involving average difficulty writing tasks [S8]. Additionally, ChatGPT increased the chances of educational success by providing students with baseline knowledge on various topics [S10].

5 Teachers' initial attempts at utilizing ChatGPT in teaching and main findings from teachers' perspective

5.1 valuable resource for teaching.

The reviewed studies showed that teachers have employed ChatGPT to recommend, modify, and generate diverse, creative, organized, and engaging educational contents, teaching materials, and testing resources more rapidly [S4], [S6], [S10] and [S11]. Additionally, teachers experienced increased productivity as ChatGPT facilitated quick and accurate responses to questions, fact-checking, and information searches [S1]. It also proved valuable in constructing new knowledge [S6] and providing timely answers to students' questions in classrooms [S11]. Moreover, ChatGPT enhanced teachers' efficiency by generating new ideas for activities and preplanning activities for their students [S4] and [S6], including interactive language game partners [S11].

5.2 Improving productivity and efficiency

The reviewed studies showed that participants' productivity and work efficiency have been significantly enhanced by using ChatGPT as it enabled them to allocate more time to other tasks and reduce their overall workloads [S6], [S10], [S11], [S13], and [S14]. However, three studies [S1], [S4], and [S11], indicated a negative perception and attitude among teachers toward using ChatGPT. This negativity stemmed from a lack of necessary skills to use it effectively [S1], a limited familiarity with it [S4], and occasional inaccuracies in the content provided by it [S10].

5.3 Catalyzing new teaching methodologies

Five of the reviewed studies highlighted that educators found the necessity of redefining their teaching profession with the assistance of ChatGPT [S11], developing new effective learning strategies [S4], and adapting teaching strategies and methodologies to ensure the development of essential skills for future engineers [S5]. They also emphasized the importance of adopting new educational philosophies and approaches that can evolve with the introduction of ChatGPT into the classroom [S12]. Furthermore, updating curricula to focus on improving human-specific features, such as emotional intelligence, creativity, and philosophical perspectives [S13], was found to be essential.

5.4 Effective utilization of CHATGPT in teaching

According to the reviewed studies, effective utilization of ChatGPT in education requires providing teachers with well-structured training, support, and adequate background on how to use ChatGPT responsibly [S1], [S3], [S11], and [S12]. Establishing clear rules and regulations regarding its usage is essential to ensure it positively impacts the teaching and learning processes, including students' skills [S1], [S4], [S5], [S8], [S9], and [S11]-[S14]. Moreover, conducting further research and engaging in discussions with policymakers and stakeholders is indeed crucial for the successful integration of ChatGPT in education and to maximize the benefits for both educators and students [S1], [S6]-[S10], and [S12]-[S14].

6 Discussion

The purpose of this review is to conduct a systematic review of empirical studies that have explored the utilization of ChatGPT, one of today’s most advanced LLM-based chatbots, in education. The findings of the reviewed studies showed several ways of ChatGPT utilization in different learning and teaching practices as well as it provided insights and considerations that can facilitate its effective and responsible use in future educational contexts. The results of the reviewed studies came from diverse fields of education, which helped us avoid a biased review that is limited to a specific field. Similarly, the reviewed studies have been conducted across different geographic regions. This kind of variety in geographic representation enriched the findings of this review.

In response to RQ1 , "What are students' and teachers' initial attempts at utilizing ChatGPT in education?", the findings from this review provide comprehensive insights. Chatbots, including ChatGPT, play a crucial role in supporting student learning, enhancing their learning experiences, and facilitating diverse learning approaches [ 42 , 43 ]. This review found that this tool, ChatGPT, has been instrumental in enhancing students' learning experiences by serving as a virtual intelligent assistant, providing immediate feedback, on-demand answers, and engaging in educational conversations. Additionally, students have benefited from ChatGPT’s ability to generate ideas, compose essays, and perform tasks like summarizing, translating, paraphrasing texts, or checking grammar, thereby enhancing their writing and language competencies. Furthermore, students have turned to ChatGPT for assistance in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks, which fosters a supportive home learning environment, allowing them to take responsibility for their own learning and cultivate the skills and approaches essential for supportive home learning environment [ 26 , 27 , 28 ]. This finding aligns with the study of Saqr et al. [ 68 , 69 ] who highlighted that, when students actively engage in their own learning process, it yields additional advantages, such as heightened motivation, enhanced achievement, and the cultivation of enthusiasm, turning them into advocates for their own learning.

Moreover, students have utilized ChatGPT for tailored teaching and step-by-step guidance on diverse educational topics, streamlining task and project completion, and generating and recommending educational content. This personalization enhances the learning environment, leading to increased academic success. This finding aligns with other recent studies [ 26 , 27 , 28 , 60 , 66 ] which revealed that ChatGPT has the potential to offer personalized learning experiences and support an effective learning process by providing students with customized feedback and explanations tailored to their needs and abilities. Ultimately, fostering students' performance, engagement, and motivation, leading to increase students' academic success [ 14 , 44 , 58 ]. This ultimate outcome is in line with the findings of Saqr et al. [ 68 , 69 ], which emphasized that learning strategies are important catalysts of students' learning, as students who utilize effective learning strategies are more likely to have better academic achievement.

Teachers, too, have capitalized on ChatGPT's capabilities to enhance productivity and efficiency, using it for creating lesson plans, generating quizzes, providing additional resources, generating and preplanning new ideas for activities, and aiding in answering students’ questions. This adoption of technology introduces new opportunities to support teaching and learning practices, enhancing teacher productivity. This finding aligns with those of Day [ 17 ], De Castro [ 18 ], and Su and Yang [ 74 ] as well as with those of Valtonen et al. [ 82 ], who revealed that emerging technological advancements have opened up novel opportunities and means to support teaching and learning practices, and enhance teachers’ productivity.

In response to RQ2 , "What are the main findings derived from empirical studies that have incorporated ChatGPT into learning and teaching?", the findings from this review provide profound insights and raise significant concerns. Starting with the insights, chatbots, including ChatGPT, have demonstrated the potential to reshape and revolutionize education, creating new, novel opportunities for enhancing the learning process and outcomes [ 83 ], facilitating different learning approaches, and offering a range of pedagogical benefits [ 19 , 43 , 72 ]. In this context, this review found that ChatGPT could open avenues for educators to adopt or develop new effective learning and teaching strategies that can evolve with the introduction of ChatGPT into the classroom. Nonetheless, there is an evident lack of research understanding regarding the potential impact of generative machine learning models within diverse educational settings [ 83 ]. This necessitates teachers to attain a high level of proficiency in incorporating chatbots, such as ChatGPT, into their classrooms to create inventive, well-structured, and captivating learning strategies. In the same vein, the review also found that teachers without the requisite skills to utilize ChatGPT realized that it did not contribute positively to their work and could potentially have adverse effects [ 37 ]. This concern could lead to inequity of access to the benefits of chatbots, including ChatGPT, as individuals who lack the necessary expertise may not be able to harness their full potential, resulting in disparities in educational outcomes and opportunities. Therefore, immediate action is needed to address these potential issues. A potential solution is offering training, support, and competency development for teachers to ensure that all of them can leverage chatbots, including ChatGPT, effectively and equitably in their educational practices [ 5 , 28 , 80 ], which could enhance accessibility and inclusivity, and potentially result in innovative outcomes [ 82 , 83 ].

Additionally, chatbots, including ChatGPT, have the potential to significantly impact students' thinking abilities, including retention, reasoning, analysis skills [ 19 , 45 ], and foster innovation and creativity capabilities [ 83 ]. This review found that ChatGPT could contribute to improving a wide range of skills among students. However, it found that frequent use of ChatGPT may result in a decrease in innovative capacities, collaborative skills and cognitive capacities, and students' motivation to attend classes, as well as could lead to reduced higher-order thinking skills among students [ 22 , 29 ]. Therefore, immediate action is needed to carefully examine the long-term impact of chatbots such as ChatGPT, on learning outcomes as well as to explore its incorporation into educational settings as a supportive tool without compromising students' cognitive development and critical thinking abilities. In the same vein, the review also found that it is challenging to draw a consistent conclusion regarding the potential of ChatGPT to aid self-directed learning approach. This finding aligns with the recent study of Baskara [ 8 ]. Therefore, further research is needed to explore the potential of ChatGPT for self-directed learning. One potential solution involves utilizing learning analytics as a novel approach to examine various aspects of students' learning and support them in their individual endeavors [ 32 ]. This approach can bridge this gap by facilitating an in-depth analysis of how learners engage with ChatGPT, identifying trends in self-directed learning behavior, and assessing its influence on their outcomes.

Turning to the significant concerns, on the other hand, a fundamental challenge with LLM-based chatbots, including ChatGPT, is the accuracy and quality of the provided information and responses, as they provide false information as truth—a phenomenon often referred to as "hallucination" [ 3 , 49 ]. In this context, this review found that the provided information was not entirely satisfactory. Consequently, the utilization of chatbots presents potential concerns, such as generating and providing inaccurate or misleading information, especially for students who utilize it to support their learning. This finding aligns with other findings [ 6 , 30 , 35 , 40 ] which revealed that incorporating chatbots such as ChatGPT, into education presents challenges related to its accuracy and reliability due to its training on a large corpus of data, which may contain inaccuracies and the way users formulate or ask ChatGPT. Therefore, immediate action is needed to address these potential issues. One possible solution is to equip students with the necessary skills and competencies, which include a background understanding of how to use it effectively and the ability to assess and evaluate the information it generates, as the accuracy and the quality of the provided information depend on the input, its complexity, the topic, and the relevance of its training data [ 28 , 49 , 86 ]. However, it's also essential to examine how learners can be educated about how these models operate, the data used in their training, and how to recognize their limitations, challenges, and issues [ 79 ].

Furthermore, chatbots present a substantial challenge concerning maintaining academic integrity [ 20 , 56 ] and copyright violations [ 83 ], which are significant concerns in education. The review found that the potential misuse of ChatGPT might foster cheating, facilitate plagiarism, and threaten academic integrity. This issue is also affirmed by the research conducted by Basic et al. [ 7 ], who presented evidence that students who utilized ChatGPT in their writing assignments had more plagiarism cases than those who did not. These findings align with the conclusions drawn by Cotton et al. [ 13 ], Hisan and Amri [ 33 ] and Sullivan et al. [ 75 ], who revealed that the integration of chatbots such as ChatGPT into education poses a significant challenge to the preservation of academic integrity. Moreover, chatbots, including ChatGPT, have increased the difficulty in identifying plagiarism [ 47 , 67 , 76 ]. The findings from previous studies [ 1 , 84 ] indicate that AI-generated text often went undetected by plagiarism software, such as Turnitin. However, Turnitin and other similar plagiarism detection tools, such as ZeroGPT, GPTZero, and Copyleaks, have since evolved, incorporating enhanced techniques to detect AI-generated text, despite the possibility of false positives, as noted in different studies that have found these tools still not yet fully ready to accurately and reliably identify AI-generated text [ 10 , 51 ], and new novel detection methods may need to be created and implemented for AI-generated text detection [ 4 ]. This potential issue could lead to another concern, which is the difficulty of accurately evaluating student performance when they utilize chatbots such as ChatGPT assistance in their assignments. Consequently, the most LLM-driven chatbots present a substantial challenge to traditional assessments [ 64 ]. The findings from previous studies indicate the importance of rethinking, improving, and redesigning innovative assessment methods in the era of chatbots [ 14 , 20 , 64 , 75 ]. These methods should prioritize the process of evaluating students' ability to apply knowledge to complex cases and demonstrate comprehension, rather than solely focusing on the final product for assessment. Therefore, immediate action is needed to address these potential issues. One possible solution would be the development of clear guidelines, regulatory policies, and pedagogical guidance. These measures would help regulate the proper and ethical utilization of chatbots, such as ChatGPT, and must be established before their introduction to students [ 35 , 38 , 39 , 41 , 89 ].

In summary, our review has delved into the utilization of ChatGPT, a prominent example of chatbots, in education, addressing the question of how ChatGPT has been utilized in education. However, there remain significant gaps, which necessitate further research to shed light on this area.

7 Conclusions

This systematic review has shed light on the varied initial attempts at incorporating ChatGPT into education by both learners and educators, while also offering insights and considerations that can facilitate its effective and responsible use in future educational contexts. From the analysis of 14 selected studies, the review revealed the dual-edged impact of ChatGPT in educational settings. On the positive side, ChatGPT significantly aided the learning process in various ways. Learners have used it as a virtual intelligent assistant, benefiting from its ability to provide immediate feedback, on-demand answers, and easy access to educational resources. Additionally, it was clear that learners have used it to enhance their writing and language skills, engaging in practices such as generating ideas, composing essays, and performing tasks like summarizing, translating, paraphrasing texts, or checking grammar. Importantly, other learners have utilized it in supporting and facilitating their directed and personalized learning on a broad range of educational topics, assisting in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks. Educators, on the other hand, found ChatGPT beneficial for enhancing productivity and efficiency. They used it for creating lesson plans, generating quizzes, providing additional resources, and answers learners' questions, which saved time and allowed for more dynamic and engaging teaching strategies and methodologies.

However, the review also pointed out negative impacts. The results revealed that overuse of ChatGPT could decrease innovative capacities and collaborative learning among learners. Specifically, relying too much on ChatGPT for quick answers can inhibit learners' critical thinking and problem-solving skills. Learners might not engage deeply with the material or consider multiple solutions to a problem. This tendency was particularly evident in group projects, where learners preferred consulting ChatGPT individually for solutions over brainstorming and collaborating with peers, which negatively affected their teamwork abilities. On a broader level, integrating ChatGPT into education has also raised several concerns, including the potential for providing inaccurate or misleading information, issues of inequity in access, challenges related to academic integrity, and the possibility of misusing the technology.

Accordingly, this review emphasizes the urgency of developing clear rules, policies, and regulations to ensure ChatGPT's effective and responsible use in educational settings, alongside other chatbots, by both learners and educators. This requires providing well-structured training to educate them on responsible usage and understanding its limitations, along with offering sufficient background information. Moreover, it highlights the importance of rethinking, improving, and redesigning innovative teaching and assessment methods in the era of ChatGPT. Furthermore, conducting further research and engaging in discussions with policymakers and stakeholders are essential steps to maximize the benefits for both educators and learners and ensure academic integrity.

It is important to acknowledge that this review has certain limitations. Firstly, the limited inclusion of reviewed studies can be attributed to several reasons, including the novelty of the technology, as new technologies often face initial skepticism and cautious adoption; the lack of clear guidelines or best practices for leveraging this technology for educational purposes; and institutional or governmental policies affecting the utilization of this technology in educational contexts. These factors, in turn, have affected the number of studies available for review. Secondly, the utilization of the original version of ChatGPT, based on GPT-3 or GPT-3.5, implies that new studies utilizing the updated version, GPT-4 may lead to different findings. Therefore, conducting follow-up systematic reviews is essential once more empirical studies on ChatGPT are published. Additionally, long-term studies are necessary to thoroughly examine and assess the impact of ChatGPT on various educational practices.

Despite these limitations, this systematic review has highlighted the transformative potential of ChatGPT in education, revealing its diverse utilization by learners and educators alike and summarized the benefits of incorporating it into education, as well as the forefront critical concerns and challenges that must be addressed to facilitate its effective and responsible use in future educational contexts. This review could serve as an insightful resource for practitioners who seek to integrate ChatGPT into education and stimulate further research in the field.

Data availability

The data supporting our findings are available upon request.

Abbreviations

• Artificial intelligence

AI in education

Large language model

Artificial neural networks

Chat Generative Pre-Trained Transformer

Recurrent neural networks

Long short-term memory

Reinforcement learning from human feedback

Natural language processing

Preferred Reporting Items for Systematic Reviews and Meta-Analyses

AlAfnan MA, Dishari S, Jovic M, Lomidze K. ChatGPT as an educational tool: opportunities, challenges, and recommendations for communication, business writing, and composition courses. J Artif Intell Technol. 2023. https://doi.org/10.37965/jait.2023.0184 .

Article   Google Scholar  

Ali JKM, Shamsan MAA, Hezam TA, Mohammed AAQ. Impact of ChatGPT on learning motivation. J Engl Stud Arabia Felix. 2023;2(1):41–9. https://doi.org/10.56540/jesaf.v2i1.51 .

Alkaissi H, McFarlane SI. Artificial hallucinations in ChatGPT: implications in scientific writing. Cureus. 2023. https://doi.org/10.7759/cureus.35179 .

Anderson N, Belavý DL, Perle SM, Hendricks S, Hespanhol L, Verhagen E, Memon AR. AI did not write this manuscript, or did it? Can we trick the AI text detector into generated texts? The potential future of ChatGPT and AI in sports & exercise medicine manuscript generation. BMJ Open Sport Exerc Med. 2023;9(1): e001568. https://doi.org/10.1136/bmjsem-2023-001568 .

Ausat AMA, Massang B, Efendi M, Nofirman N, Riady Y. Can chat GPT replace the role of the teacher in the classroom: a fundamental analysis. J Educ. 2023;5(4):16100–6.

Google Scholar  

Baidoo-Anu D, Ansah L. Education in the Era of generative artificial intelligence (AI): understanding the potential benefits of ChatGPT in promoting teaching and learning. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4337484 .

Basic Z, Banovac A, Kruzic I, Jerkovic I. Better by you, better than me, chatgpt3 as writing assistance in students essays. 2023. arXiv preprint arXiv:2302.04536 .‏

Baskara FR. The promises and pitfalls of using chat GPT for self-determined learning in higher education: an argumentative review. Prosiding Seminar Nasional Fakultas Tarbiyah dan Ilmu Keguruan IAIM Sinjai. 2023;2:95–101. https://doi.org/10.47435/sentikjar.v2i0.1825 .

Behera RK, Bala PK, Dhir A. The emerging role of cognitive computing in healthcare: a systematic literature review. Int J Med Inform. 2019;129:154–66. https://doi.org/10.1016/j.ijmedinf.2019.04.024 .

Chaka C. Detecting AI content in responses generated by ChatGPT, YouChat, and Chatsonic: the case of five AI content detection tools. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.2.12 .

Chiu TKF, Xia Q, Zhou X, Chai CS, Cheng M. Systematic literature review on opportunities, challenges, and future research recommendations of artificial intelligence in education. Comput Educ Artif Intell. 2023;4:100118. https://doi.org/10.1016/j.caeai.2022.100118 .

Choi EPH, Lee JJ, Ho M, Kwok JYY, Lok KYW. Chatting or cheating? The impacts of ChatGPT and other artificial intelligence language models on nurse education. Nurse Educ Today. 2023;125:105796. https://doi.org/10.1016/j.nedt.2023.105796 .

Cotton D, Cotton PA, Shipway JR. Chatting and cheating: ensuring academic integrity in the era of ChatGPT. Innov Educ Teach Int. 2023. https://doi.org/10.1080/14703297.2023.2190148 .

Crawford J, Cowling M, Allen K. Leadership is needed for ethical ChatGPT: Character, assessment, and learning using artificial intelligence (AI). J Univ Teach Learn Pract. 2023. https://doi.org/10.53761/1.20.3.02 .

Creswell JW. Educational research: planning, conducting, and evaluating quantitative and qualitative research [Ebook]. 4th ed. London: Pearson Education; 2015.

Curry D. ChatGPT Revenue and Usage Statistics (2023)—Business of Apps. 2023. https://www.businessofapps.com/data/chatgpt-statistics/

Day T. A preliminary investigation of fake peer-reviewed citations and references generated by ChatGPT. Prof Geogr. 2023. https://doi.org/10.1080/00330124.2023.2190373 .

De Castro CA. A Discussion about the Impact of ChatGPT in education: benefits and concerns. J Bus Theor Pract. 2023;11(2):p28. https://doi.org/10.22158/jbtp.v11n2p28 .

Deng X, Yu Z. A meta-analysis and systematic review of the effect of Chatbot technology use in sustainable education. Sustainability. 2023;15(4):2940. https://doi.org/10.3390/su15042940 .

Eke DO. ChatGPT and the rise of generative AI: threat to academic integrity? J Responsib Technol. 2023;13:100060. https://doi.org/10.1016/j.jrt.2023.100060 .

Elmoazen R, Saqr M, Tedre M, Hirsto L. A systematic literature review of empirical research on epistemic network analysis in education. IEEE Access. 2022;10:17330–48. https://doi.org/10.1109/access.2022.3149812 .

Farrokhnia M, Banihashem SK, Noroozi O, Wals AEJ. A SWOT analysis of ChatGPT: implications for educational practice and research. Innov Educ Teach Int. 2023. https://doi.org/10.1080/14703297.2023.2195846 .

Fergus S, Botha M, Ostovar M. Evaluating academic answers generated using ChatGPT. J Chem Educ. 2023;100(4):1672–5. https://doi.org/10.1021/acs.jchemed.3c00087 .

Fink A. Conducting research literature reviews: from the Internet to Paper. Incorporated: SAGE Publications; 2010.

Firaina R, Sulisworo D. Exploring the usage of ChatGPT in higher education: frequency and impact on productivity. Buletin Edukasi Indonesia (BEI). 2023;2(01):39–46. https://doi.org/10.56741/bei.v2i01.310 .

Firat, M. (2023). How chat GPT can transform autodidactic experiences and open education.  Department of Distance Education, Open Education Faculty, Anadolu Unive .‏ https://orcid.org/0000-0001-8707-5918

Firat M. What ChatGPT means for universities: perceptions of scholars and students. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.22 .

Fuchs K. Exploring the opportunities and challenges of NLP models in higher education: is Chat GPT a blessing or a curse? Front Educ. 2023. https://doi.org/10.3389/feduc.2023.1166682 .

García-Peñalvo FJ. La percepción de la inteligencia artificial en contextos educativos tras el lanzamiento de ChatGPT: disrupción o pánico. Educ Knowl Soc. 2023;24: e31279. https://doi.org/10.14201/eks.31279 .

Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor A, Chartash D. How does ChatGPT perform on the United States medical Licensing examination? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ. 2023;9: e45312. https://doi.org/10.2196/45312 .

Hashana AJ, Brundha P, Ayoobkhan MUA, Fazila S. Deep Learning in ChatGPT—A Survey. In   2023 7th international conference on trends in electronics and informatics (ICOEI) . 2023. (pp. 1001–1005). IEEE. https://doi.org/10.1109/icoei56765.2023.10125852

Hirsto L, Saqr M, López-Pernas S, Valtonen T. (2022). A systematic narrative review of learning analytics research in K-12 and schools.  Proceedings . https://ceur-ws.org/Vol-3383/FLAIEC22_paper_9536.pdf

Hisan UK, Amri MM. ChatGPT and medical education: a double-edged sword. J Pedag Educ Sci. 2023;2(01):71–89. https://doi.org/10.13140/RG.2.2.31280.23043/1 .

Hopkins AM, Logan JM, Kichenadasse G, Sorich MJ. Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift. JNCI Cancer Spectr. 2023. https://doi.org/10.1093/jncics/pkad010 .

Househ M, AlSaad R, Alhuwail D, Ahmed A, Healy MG, Latifi S, Sheikh J. Large Language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ. 2023;9: e48291. https://doi.org/10.2196/48291 .

Ilkka T. The impact of artificial intelligence on learning, teaching, and education. Minist de Educ. 2018. https://doi.org/10.2760/12297 .

Iqbal N, Ahmed H, Azhar KA. Exploring teachers’ attitudes towards using CHATGPT. Globa J Manag Adm Sci. 2022;3(4):97–111. https://doi.org/10.46568/gjmas.v3i4.163 .

Irfan M, Murray L, Ali S. Integration of Artificial intelligence in academia: a case study of critical teaching and learning in Higher education. Globa Soc Sci Rev. 2023;8(1):352–64. https://doi.org/10.31703/gssr.2023(viii-i).32 .

Jeon JH, Lee S. Large language models in education: a focus on the complementary relationship between human teachers and ChatGPT. Educ Inf Technol. 2023. https://doi.org/10.1007/s10639-023-11834-1 .

Khan RA, Jawaid M, Khan AR, Sajjad M. ChatGPT—Reshaping medical education and clinical management. Pak J Med Sci. 2023. https://doi.org/10.12669/pjms.39.2.7653 .

King MR. A conversation on artificial intelligence, Chatbots, and plagiarism in higher education. Cell Mol Bioeng. 2023;16(1):1–2. https://doi.org/10.1007/s12195-022-00754-8 .

Kooli C. Chatbots in education and research: a critical examination of ethical implications and solutions. Sustainability. 2023;15(7):5614. https://doi.org/10.3390/su15075614 .

Kuhail MA, Alturki N, Alramlawi S, Alhejori K. Interacting with educational chatbots: a systematic review. Educ Inf Technol. 2022;28(1):973–1018. https://doi.org/10.1007/s10639-022-11177-3 .

Lee H. The rise of ChatGPT: exploring its potential in medical education. Anat Sci Educ. 2023. https://doi.org/10.1002/ase.2270 .

Li L, Subbareddy R, Raghavendra CG. AI intelligence Chatbot to improve students learning in the higher education platform. J Interconnect Netw. 2022. https://doi.org/10.1142/s0219265921430325 .

Limna P. A Review of Artificial Intelligence (AI) in Education during the Digital Era. 2022. https://ssrn.com/abstract=4160798

Lo CK. What is the impact of ChatGPT on education? A rapid review of the literature. Educ Sci. 2023;13(4):410. https://doi.org/10.3390/educsci13040410 .

Luo W, He H, Liu J, Berson IR, Berson MJ, Zhou Y, Li H. Aladdin’s genie or pandora’s box For early childhood education? Experts chat on the roles, challenges, and developments of ChatGPT. Early Educ Dev. 2023. https://doi.org/10.1080/10409289.2023.2214181 .

Meyer JG, Urbanowicz RJ, Martin P, O’Connor K, Li R, Peng P, Moore JH. ChatGPT and large language models in academia: opportunities and challenges. Biodata Min. 2023. https://doi.org/10.1186/s13040-023-00339-9 .

Mhlanga D. Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4354422 .

Neumann, M., Rauschenberger, M., & Schön, E. M. (2023). “We Need To Talk About ChatGPT”: The Future of AI and Higher Education.‏ https://doi.org/10.1109/seeng59157.2023.00010

Nolan B. Here are the schools and colleges that have banned the use of ChatGPT over plagiarism and misinformation fears. Business Insider . 2023. https://www.businessinsider.com

O’Leary DE. An analysis of three chatbots: BlenderBot, ChatGPT and LaMDA. Int J Intell Syst Account, Financ Manag. 2023;30(1):41–54. https://doi.org/10.1002/isaf.1531 .

Okoli C. A guide to conducting a standalone systematic literature review. Commun Assoc Inf Syst. 2015. https://doi.org/10.17705/1cais.03743 .

OpenAI. (2023). https://openai.com/blog/chatgpt

Perkins M. Academic integrity considerations of AI large language models in the post-pandemic era: ChatGPT and beyond. J Univ Teach Learn Pract. 2023. https://doi.org/10.53761/1.20.02.07 .

Plevris V, Papazafeiropoulos G, Rios AJ. Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard. arXiv (Cornell University) . 2023. https://doi.org/10.48550/arxiv.2305.18618

Rahman MM, Watanobe Y (2023) ChatGPT for education and research: opportunities, threats, and strategies. Appl Sci 13(9):5783. https://doi.org/10.3390/app13095783

Ram B, Verma P. Artificial intelligence AI-based Chatbot study of ChatGPT, google AI bard and baidu AI. World J Adv Eng Technol Sci. 2023;8(1):258–61. https://doi.org/10.30574/wjaets.2023.8.1.0045 .

Rasul T, Nair S, Kalendra D, Robin M, de Oliveira Santini F, Ladeira WJ, Heathcote L. The role of ChatGPT in higher education: benefits, challenges, and future research directions. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.29 .

Ratnam M, Sharm B, Tomer A. ChatGPT: educational artificial intelligence. Int J Adv Trends Comput Sci Eng. 2023;12(2):84–91. https://doi.org/10.30534/ijatcse/2023/091222023 .

Ray PP. ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber-Phys Syst. 2023;3:121–54. https://doi.org/10.1016/j.iotcps.2023.04.003 .

Roumeliotis KI, Tselikas ND. ChatGPT and Open-AI models: a preliminary review. Future Internet. 2023;15(6):192. https://doi.org/10.3390/fi15060192 .

Rudolph J, Tan S, Tan S. War of the chatbots: Bard, Bing Chat, ChatGPT, Ernie and beyond. The new AI gold rush and its impact on higher education. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.23 .

Ruiz LMS, Moll-López S, Nuñez-Pérez A, Moraño J, Vega-Fleitas E. ChatGPT challenges blended learning methodologies in engineering education: a case study in mathematics. Appl Sci. 2023;13(10):6039. https://doi.org/10.3390/app13106039 .

Sallam M, Salim NA, Barakat M, Al-Tammemi AB. ChatGPT applications in medical, dental, pharmacy, and public health education: a descriptive study highlighting the advantages and limitations. Narra J. 2023;3(1): e103. https://doi.org/10.52225/narra.v3i1.103 .

Salvagno M, Taccone FS, Gerli AG. Can artificial intelligence help for scientific writing? Crit Care. 2023. https://doi.org/10.1186/s13054-023-04380-2 .

Saqr M, López-Pernas S, Helske S, Hrastinski S. The longitudinal association between engagement and achievement varies by time, students’ profiles, and achievement state: a full program study. Comput Educ. 2023;199:104787. https://doi.org/10.1016/j.compedu.2023.104787 .

Saqr M, Matcha W, Uzir N, Jovanović J, Gašević D, López-Pernas S. Transferring effective learning strategies across learning contexts matters: a study in problem-based learning. Australas J Educ Technol. 2023;39(3):9.

Schöbel S, Schmitt A, Benner D, Saqr M, Janson A, Leimeister JM. Charting the evolution and future of conversational agents: a research agenda along five waves and new frontiers. Inf Syst Front. 2023. https://doi.org/10.1007/s10796-023-10375-9 .

Shoufan A. Exploring students’ perceptions of CHATGPT: thematic analysis and follow-up survey. IEEE Access. 2023. https://doi.org/10.1109/access.2023.3268224 .

Sonderegger S, Seufert S. Chatbot-mediated learning: conceptual framework for the design of Chatbot use cases in education. Gallen: Institute for Educational Management and Technologies, University of St; 2022. https://doi.org/10.5220/0010999200003182 .

Book   Google Scholar  

Strzelecki A. To use or not to use ChatGPT in higher education? A study of students’ acceptance and use of technology. Interact Learn Environ. 2023. https://doi.org/10.1080/10494820.2023.2209881 .

Su J, Yang W. Unlocking the power of ChatGPT: a framework for applying generative AI in education. ECNU Rev Educ. 2023. https://doi.org/10.1177/20965311231168423 .

Sullivan M, Kelly A, McLaughlan P. ChatGPT in higher education: Considerations for academic integrity and student learning. J ApplLearn Teach. 2023;6(1):1–10. https://doi.org/10.37074/jalt.2023.6.1.17 .

Szabo A. ChatGPT is a breakthrough in science and education but fails a test in sports and exercise psychology. Balt J Sport Health Sci. 2023;1(128):25–40. https://doi.org/10.33607/bjshs.v127i4.1233 .

Taecharungroj V. “What can ChatGPT do?” analyzing early reactions to the innovative AI chatbot on Twitter. Big Data Cognit Comput. 2023;7(1):35. https://doi.org/10.3390/bdcc7010035 .

Tam S, Said RB. User preferences for ChatGPT-powered conversational interfaces versus traditional methods. Biomed Eng Soc. 2023. https://doi.org/10.58496/mjcsc/2023/004 .

Tedre M, Kahila J, Vartiainen H. (2023). Exploration on how co-designing with AI facilitates critical evaluation of ethics of AI in craft education. In: Langran E, Christensen P, Sanson J (Eds).  Proceedings of Society for Information Technology and Teacher Education International Conference . 2023. pp. 2289–2296.

Tlili A, Shehata B, Adarkwah MA, Bozkurt A, Hickey DT, Huang R, Agyemang B. What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education. Smart Learn Environ. 2023. https://doi.org/10.1186/s40561-023-00237-x .

Uddin SMJ, Albert A, Ovid A, Alsharef A. Leveraging CHATGPT to aid construction hazard recognition and support safety education and training. Sustainability. 2023;15(9):7121. https://doi.org/10.3390/su15097121 .

Valtonen T, López-Pernas S, Saqr M, Vartiainen H, Sointu E, Tedre M. The nature and building blocks of educational technology research. Comput Hum Behav. 2022;128:107123. https://doi.org/10.1016/j.chb.2021.107123 .

Vartiainen H, Tedre M. Using artificial intelligence in craft education: crafting with text-to-image generative models. Digit Creat. 2023;34(1):1–21. https://doi.org/10.1080/14626268.2023.2174557 .

Ventayen RJM. OpenAI ChatGPT generated results: similarity index of artificial intelligence-based contents. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4332664 .

Wagner MW, Ertl-Wagner BB. Accuracy of information and references using ChatGPT-3 for retrieval of clinical radiological information. Can Assoc Radiol J. 2023. https://doi.org/10.1177/08465371231171125 .

Wardat Y, Tashtoush MA, AlAli R, Jarrah AM. ChatGPT: a revolutionary tool for teaching and learning mathematics. Eurasia J Math, Sci Technol Educ. 2023;19(7):em2286. https://doi.org/10.29333/ejmste/13272 .

Webster J, Watson RT. Analyzing the past to prepare for the future: writing a literature review. Manag Inf Syst Quart. 2002;26(2):3.

Xiao Y, Watson ME. Guidance on conducting a systematic literature review. J Plan Educ Res. 2017;39(1):93–112. https://doi.org/10.1177/0739456x17723971 .

Yan D. Impact of ChatGPT on learners in a L2 writing practicum: an exploratory investigation. Educ Inf Technol. 2023. https://doi.org/10.1007/s10639-023-11742-4 .

Yu H. Reflection on whether Chat GPT should be banned by academia from the perspective of education and teaching. Front Psychol. 2023;14:1181712. https://doi.org/10.3389/fpsyg.2023.1181712 .

Zhu C, Sun M, Luo J, Li T, Wang M. How to harness the potential of ChatGPT in education? Knowl Manag ELearn. 2023;15(2):133–52. https://doi.org/10.34105/j.kmel.2023.15.008 .

Download references

The paper is co-funded by the Academy of Finland (Suomen Akatemia) Research Council for Natural Sciences and Engineering for the project Towards precision education: Idiographic learning analytics (TOPEILA), Decision Number 350560.

Author information

Authors and affiliations.

School of Computing, University of Eastern Finland, 80100, Joensuu, Finland

Yazid Albadarin, Mohammed Saqr, Nicolas Pope & Markku Tukiainen

You can also search for this author in PubMed   Google Scholar

Contributions

YA contributed to the literature search, data analysis, discussion, and conclusion. Additionally, YA contributed to the manuscript’s writing, editing, and finalization. MS contributed to the study’s design, conceptualization, acquisition of funding, project administration, allocation of resources, supervision, validation, literature search, and analysis of results. Furthermore, MS contributed to the manuscript's writing, revising, and approving it in its finalized state. NP contributed to the results, and discussions, and provided supervision. NP also contributed to the writing process, revisions, and the final approval of the manuscript in its finalized state. MT contributed to the study's conceptualization, resource management, supervision, writing, revising the manuscript, and approving it.

Corresponding author

Correspondence to Yazid Albadarin .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

See Table  4

The process of synthesizing the data presented in Table  4 involved identifying the relevant studies through a search process of databases (ERIC, Scopus, Web of Knowledge, Dimensions.ai, and lens.org) using specific keywords "ChatGPT" and "education". Following this, inclusion/exclusion criteria were applied, and data extraction was performed using Creswell's [ 15 ] coding techniques to capture key information and identify common themes across the included studies.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Albadarin, Y., Saqr, M., Pope, N. et al. A systematic literature review of empirical research on ChatGPT in education. Discov Educ 3 , 60 (2024). https://doi.org/10.1007/s44217-024-00138-2

Download citation

Received : 22 October 2023

Accepted : 10 May 2024

Published : 26 May 2024

DOI : https://doi.org/10.1007/s44217-024-00138-2

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Large language models
• Educational technology
• Systematic review

Advertisement

• Find a journal
• Publish with us
• Track your research

The impact of AI and ChatGPT on research reporting

Affiliations.

• 1 Center for Perioperative Optimization, Department of Surgery, Herlev and Gentofte Hospital, University of Copenhagen, Copenhagen, Denmark.
• 2 Center for Perioperative Optimization, Department of Surgery, Herlev and Gentofte Hospital, University of Copenhagen, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Denmark.
• PMID: 37167941

ChatGPT and the newest GPT-4 are AI language models developed by OpenAI that have gained attention for their potential applications in biomedical research reporting. The models can assist researchers in various stages of writing scientific articles, including literature search, outlining, writing different sections, formatting, and translation. The use of ChatGPT or GPT-4 in research reporting has the potential to speed up the writing process, but its limitations, such as incorrect answers and biases, should also be considered. There is ongoing debate over the issue of AI authorship in scientific papers, with some publishers allowing it to be listed as a contributor in the acknowledgements section, while others do not allow it to be listed as an author. The use of ChatGPT or GPT-4 in research reporting is a recent development, and further studies and discussions are needed to determine their potential and limitations in this field.

• Artificial Intelligence
• Authorship*
• Biomedical Research*
• New Zealand
• Research Personnel

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.

When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.

ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form .

What is ChatGPT and why does it matter? Here's what you need to know

What is ChatGPT?

ChatGPT is an AI chatbot with natural language processing (NLP) that allows you to have human-like conversations to complete various tasks. The  generative AI  tool can answer questions and assist you with tasks such as composing emails, essays, code, and more.

Also :  How to use ChatGPT: What you need to know now

It's currently  open to use for free . A paid subscription version called ChatGPT Plus launched in February 2023 with access to priority access to OpenAI's latest models and updates.

Who made ChatGPT?

AI startup OpenAI launched ChatGPT on November 30, 2022. OpenAI has also developed  DALL-E 2  and DALL-E 3 , popular  AI image generators , and Whisper, an automatic speech recognition system. 

Who owns ChatGPT currently?

OpenAI owns ChatGPT. Microsoft is a major investor in OpenAI thanks to multiyear, multi-billion dollar  investments. Elon Musk was an investor when OpenAI was first founded in 2015, but has since completely severed ties with the startup and created his own AI chatbot, Grok .

How can you access ChatGPT?

On April 1, 2024, OpenAI stopped requiring you to log in to use ChatGPT. Now, you can access ChatGPT simply by visiting  chat.openai.com . You can also access ChatGPT  via an app on your iPhone  or  Android  device.

Once you visit the site, you can start chatting away with ChatGPT. A great way to get started is by asking a question, similar to what you would do with Google. You can ask as many questions as you'd like.

Also: ChatGPT no longer requires a login, but you might want one anyway. Here's why

There are still some perks to creating an OpenAI account, such saving and reviewing your chat history and accessing custom instructions. Creating an OpenAI account is entirely free and easy. You can even log in with your Google account.

For step-by-step instructions, check out ZDNET's guide on  how to start using ChatGPT . 

Is there a ChatGPT app?

Yes, an official ChatGPT app is available for both iPhone and Android users. 

Also: ChatGPT dropped a free app for iPhones. Does it live up to the hype?

Make sure to download OpenAI's app, as there are a plethora of copycat fake apps listed on Apple's App Store and the Google Play Store that are not affiliated with the startup.

Is ChatGPT available for free?

ChatGPT is free to use, regardless of what you use it for, including writing, coding, and much more. 

There is a subscription option , ChatGPT Plus, that users can take advantage of that costs $20/month. The paid subscription model guarantees users extra perks, such as priority access to GPT-4o and the latest upgrades. 

Also: ChatGPT vs ChatGPT Plus: Is it worth the subscription fee?

Although the subscription price may seem steep, it is the same amount as Microsoft Copilot Pro and Google One AI, Microsoft's and Google's premium AI offerings. 

The free version is still a solid option as it can access the same model and most of the same perks. One major exception: only subscribers get guaranteed access to GPT-4o when the model is at capacity. 

I tried using ChatGPT and it says it's at capacity. What does that mean?

The ChatGPT website operates using servers. When too many people hop onto these servers, they may overload and can't process your request. If this happens to you, you can visit the site later when fewer people are trying to access the tool. You can also keep the tab open and refresh it periodically. 

Also: The best AI chatbots

If you want to skip the wait and have reliable access, you can subscribe to  ChatGPT Plus  for general access during peak times, faster response times, and priority access to new features and improvements, including priority access to GPT-4o.

You can also try using Bing's AI chatbot, Copilot . This chatbot is free to use, runs on GPT-4, has no wait times, and can access the internet for more accurate information.

What is ChatGPT used for?

ChatGPT has many functions in addition to answering simple questions. ChatGPT can compose essays , have philosophical conversations, do math, and even code for you . 

The tasks ChatGPT can help with also don't have to be so ambitious. For example, my favorite use of ChatGPT is for help creating basic lists for chores, such as packing and grocery shopping, and to-do lists that make my daily life more productive. The possibilities are endless. 

ZDNET has published many ChatGPT how-to guides. Below are some of the most popular ones. 

Use ChatGPT to: 

• Write an essay
• Create an app
• Build your resume
• Write Excel formulas
• Summarize content
• Write a cover letter
• Start an Etsy business
• Create charts and tables
• Write Adruino drivers

Can ChatGPT generate images?

Yes, ChatGPT can generate images, but only for ChatGPT Plus subscribers. Since OpenAI discontinued DALL-E 2 in February 2024, the only way to access its most advanced AI image generator, DALL-E 3, through OpenAI's offerings is via its chatbot and ChatGPT Plus subscription.

Also: DALL-E adds new ways to edit and create AI-generated images. Learn how to use it

Microsoft's Copilot offers image generation, which is also powered by DALL-E 3, in its chatbot for free. This is a great alternative if you don't want to shell out the money for ChatGPT Plus.

How does ChatGPT work?

ChatGPT runs on a large language model (LLM) architecture created by OpenAI called the  Generative Pre-trained Transformer  (GPT). Since its launch, the free version of ChatGPT ran on a fine-tuned model in the GPT-3.5 series until May 2024, when the startup upgraded the model to GPT-4o. 

Also:   Here's a deep dive into how ChatGPT works  

With a subscription to ChatGPT Plus , you can access GPT-3.5, GPT-4, or  GPT-4o . Plus, users also have the added perk of priority access to GPT-4o, even when it is at capacity, while free users get booted down to GPT-3.5. 

Generative AI models of this type are trained on vast amounts of information from the internet, including websites, books, news articles, and more.

What does ChatGPT stand for?

As mentioned above, the last three letters in ChatGPT's namesake stand for Generative Pre-trained Transformer (GPT), a family of large language models created by OpenAI that uses deep learning to generate human-like, conversational text. 

Also: What does GPT stand for? Understanding GPT 3.5, GPT 4, GPT-4 Turbo, and more

The "Chat" part of the name is simply a callout to its chatting capabilities. 

Is ChatGPT better than a search engine?

ChatGPT is a language model created to converse with the end user. A search engine indexes web pages on the internet to help users find information. One is not better than the other, as each suit different purposes. 

When searching for as much up-to-date, accurate information as you can access, your best bet is a search engine. It will provide you with pages upon pages of sources you can peruse. 

Also: The best AI search engines of 2024: Google, Perplexity, and more

As of May, the free version of ChatGPT can get responses from both the GPT-4o model and the web. It will only pull its answer from, and ultimately list, a handful of sources, as opposed to showing nearly endless search results.

For example, I used GPT-4o to answer, "What is the weather today in San Francisco?" The response told me it searched four sites and provided links to them. 

If you are looking for a platform that can explain complex topics in an easy-to-understand manner, then ChatGPT might be what you want. If you want the best of both worlds, there are plenty of AI search engines on the market that combine both.

What are ChatGPT's limitations?

Despite its impressive capabilities, ChatGPT still has limitations. Users sometimes need to reword questions multiple times for ChatGPT to understand their intent. A bigger limitation is a lack of quality in responses, which can sometimes be plausible-sounding but are verbose or make no practical sense. 

Instead of asking for clarification on ambiguous questions, the model guesses what your question means, which can lead to poor responses. Generative AI models are also subject to hallucinations, which can result in inaccurate responses.

Does ChatGPT give wrong answers?

As mentioned above, ChatGPT, like all language models, has  limitations  and can give nonsensical answers and incorrect information, so it's important to double-check the data it gives you.

Also: 8 ways to reduce ChatGPT hallucinations

OpenAI recommends that you provide feedback on what ChatGPT generates by using the thumbs-up and thumbs-down buttons to improve its underlying model. You can even join the startup's Bug Bounty program , which offers up to $20,000 for reporting security bugs and safety issues.

Can ChatGPT refuse to answer my prompts?

AI systems like ChatGPT can and do reject  inappropriate requests . The AI assistant can identify inappropriate submissions to prevent the generation of unsafe content.

Also:  6 things ChatGPT can't do (and another 20 it refuses to do)

These submissions include questions that violate someone's rights, are offensive, are discriminatory, or involve illegal activities. The ChatGPT model can also challenge incorrect premises, answer follow-up questions, and even admit mistakes when you point them out.

These guardrails are important. AI models can generate advanced, realistic content that can be exploited by bad actors for harm, such as spreading misinformation about public figures and influencing elections .

Can I chat with ChatGPT?

Although some people use ChatGPT for elaborate functions, such as writing code or even malware , you can use ChatGPT for more mundane activities, such as having a friendly conversation. 

Also:  Do you like asking ChatGPT questions? You could get paid (a lot) for it

Some conversation starters could be as simple as, "I am hungry, what food should I get?" or as elaborate as, "What do you think happens in the afterlife?" Either way, ChatGPT is sure to have an answer for you. 

Is ChatGPT safe?

People are expressing concerns about AI chatbots replacing or atrophying human intelligence. For example, a chatbot can write an article on any topic efficiently (though not necessarily accurately) within seconds, potentially eliminating the need for human writers.

Chatbots can also write an entire essay within seconds, making it easier for students to cheat or avoid learning how to write properly. This even led  some school districts to block access  when ChatGPT initially launched. 

Also:  Generative AI can be the academic assistant an underserved student needs

Now, not only have many of those schools decided to unblock the technology, but some higher education institutions have been  catering their academic offerings  to AI-related coursework. 

Another concern with AI chatbots is the possible spread of misinformation. ChatGPT itself says: "My responses are not intended to be taken as fact, and I always encourage people to verify any information they receive from me or any other source." OpenAI also notes that ChatGPT sometimes writes "plausible-sounding but incorrect or nonsensical answers."

Also:  Microsoft and OpenAI detect and disrupt nation-state cyber threats that use AI, report shows

Lastly, there are ethical concerns regarding the information ChatGPT was trained on, since the startup scraped the internet to train the chatbot. 

It also automatically uses people's interactions with the free version of the chatbot to further train its models, raising privacy concerns. OpenAI lets you turn off training in ChatGPT's settings.

Does ChatGPT plagiarize?

Yes, sort of. OpenAI scraped the internet to train ChatGPT. Therefore, the technology's knowledge is influenced by other people's work. Since there is no guarantee that when OpenAI outputs its answers it is entirely original, the chatbot may regurgitate someone else's work in your answer, which is considered plagiarism. 

Is there a ChatGPT detector?

Concerns about students using AI to cheat mean the need for a ChatGPT text detector is becoming more evident. 

In January 2023, OpenAI released a free tool to target this problem. Unfortunately, OpenAI's "classifier" tool could only correctly identify 26% of AI-written text with a "likely AI-written" designation. Furthermore, it provided false positives 9% of the time, incorrectly identifying human-written work as AI-produced. 

The tool performed so poorly  that, six months after being released, OpenAI it shut down "due to its low rate of accuracy." Despite the tool's failure, the startup claims to be researching more effective techniques for AI text identification.

Also: OpenAI unveils text-to-video model and the results are astonishing

Other AI detectors exist on the market, including GPT-2 Output Detector ,  Writer AI Content Detector , and Content at Scale's AI Content Detection  tool. ZDNET put these tools to the test, and the results were underwhelming: all three were found to be unreliable sources for spotting AI, repeatedly giving false negatives. Here are  ZDNET's full test results .

What are the common signs something was written by ChatGPT?

Although tools aren't sufficient for detecting ChatGPT-generated writing, a  study  shows that humans could detect AI-written text by looking for politeness. The study's results indicate that  ChatGPT's writing style is extremely polite . And unlike humans, it cannot produce responses that include metaphors, irony, or sarcasm.

Will my conversations with ChatGPT be used for training?

One of the major risks when using generative AI models is that they become more intelligent by being trained on user inputs. Therefore, when familiarizing yourself with how to use ChatGPT, you might wonder if your specific conversations will be used for training and, if so, who can view your chats.

Also:  This ChatGPT update fixed one of my biggest productivity issues with the AI chatbot

OpenAI will use your conversations with the free chatbot to automatically training data to refine its models. You can opt out of the startup using your data for model training by clicking on the question mark in the bottom left-hand corner, Settings, and turning off "Improve the model for everyone."

What is GPT-4?

GPT-4 is OpenAI's language model that is much more advanced than its predecessor, GPT-3.5. Users can access GPT-4 by subscribing to ChatGPT Plus for $20 per month or using Microsoft's Copilot.

Also: What does GPT stand for? Understanding GPT-3.5, GPT-4, and more

GPT-4 has advanced intellectual capabilities, meaning it outperforms GPT-3.5 in a series of simulated benchmark exams. The newer model also supposedly produces fewer hallucinations. 

What is GPT-4o?

GPT-4o is OpenAI's latest, fastest, and most advanced flagship model. As the name implies, it has the same intelligence as GPT-4. However, the "o" in the title stands for "omni," referring to its multimodal capabilities, which allow it to understand text, audio, image, and video inputs and output text, audio, and image outputs. 

Also:  6 ways OpenAI just supercharged ChatGPT for free users

The model is 50% cheaper in the API than GPT-4 Turbo while still matching its English and coding capabilities and outperforming it in non-English languages, vision, and audio understanding -- a big win for developers.

Are there alternatives to ChatGPT worth considering?

Although ChatGPT gets the most buzz, other options are just as good -- and might even be better suited to your needs. ZDNET has created a list of the best chatbots, which have all been tested by us and show which tool is best for your requirements. 

Also: 4 things Claude AI can do that ChatGPT can't

Despite ChatGPT's extensive abilities, there are major downsides to the AI chatbot. If you want to try the technology, there are plenty of other options: Copilot , Claude , Perplexity ,  Jasper , and more.  

Is ChatGPT smart enough to pass benchmark exams?

Yes, ChatGPT is capable of passing a series of benchmark exams. A professor at Wharton, the University of Pennsylvania's business school, used ChatGPT to take an MBA exam and the results were quite impressive. 

ChatGPT not only passed the exam, but the tool scored between a B- and a B. The professor, Christian Terwiesch, was impressed at its basic operations management, process analysis questions, and explanations.

OpenAI also tested the chatbot's ability to pass benchmark exams. Although ChatGPT could pass many of these benchmark exams, its scores were usually in the lower percentile. However, with GPT-4, ChatGPT can score much higher.

For example, ChatGPT using GPT-3.5 scored in the lower 10th percentile of a simulated Bar Exam, while GPT-4 scored in the top 10th percentile. You can see more examples from OpenAI in the chart below.

Can ChatGPT be used for job application assistance?

Yes, ChatGPT is a great resource to help with job applications. Undertaking a job search can be tedious and difficult, and ChatGPT can help you lighten the load. ChatGPT can build your resume  and write a cover letter .

Also :  How to use ChatGPT to write an essay

If your application has any written supplements, you can use ChatGPT to help you write those essays or personal statements . 

What are the most common ChatGPT plugins, and how do I use them?

Plugins allowed ChatGPT to connect to third-party applications, including access to real-time information on the web. The plugins expanded ChatGPT's abilities , allowing it to assist with many more activities, such as planning a trip or finding a place to eat. 

Also:  My two favorite ChatGPT Plus features and the remarkable things I can do with them

On March 19, 2024, however, OpenAI stopped allowing users to install new plugins or start new conversations with existing ones. Instead, OpenAI replaced plugins with GPTs , which are easier for developers to build. 

Users can find 3 million ChatGPT chatbots, also known as GPTs, on the GPT store. Unfortunately, there is also a lot of spam in the GPT store.

What is Microsoft's involvement with ChatGPT?

Microsoft was an early investor in OpenAI, the AI startup behind ChatGPT, long before ChatGPT was released to the public. Microsoft's first involvement with OpenAI was in 2019, when the company invested $1 billion, and then another $2 billion in the years after. In January 2023, Microsoft extended its partnership with OpenAI through a multiyear, multi-billion dollar investment .

Also: ChatGPT vs. Copilot: Which AI chatbot is better for you?

 Neither company disclosed the investment value, but unnamed sources told Bloomberg that it could total $10 billion over multiple years. In return, OpenAI's exclusive cloud-computing provider is Microsoft Azure, powering all OpenAI workloads across research, products, and API services.

Microsoft has also used its OpenAI partnership to revamp its Bing search engine and improve its browser. 

On February 7, 2023, Microsoft unveiled a new Bing tool , now known as Copilot, that runs on OpenAI's GPT-4, customized specifically for search.

What does Copilot (formerly Bing Chat) have to do with ChatGPT?

In February 2023,  Microsoft unveiled  a new version of Bing -- and its standout feature was its integration with ChatGPT. When it was announced, Microsoft shared that Bing Chat, now Copilot, was powered by a next-generation version of OpenAI's large language model, making it "more powerful than ChatGPT." Five weeks after the launch, Microsoft revealed that Copilot had been running on GPT-4 before the model had even launched. 

How does Copilot compare to ChatGPT?

Copilot uses OpenAI's GPT-4, which means that since its launch, it has been more efficient and capable than the standard, free version of ChatGPT. At the time, Copilot boasted several other features over ChatGPT, such as access to the internet, knowledge of current information, and footnotes.

In May 2024, however, OpenAI supercharged the free version of its chatbot with GPT-4o. The upgrade gave users GPT-4 level intelligence, the ability to get responses from the web via ChatGPT Browse with Bing, analyze data, chat about photos and documents, use GPTs, access the GPT Store, and Voice Mode. Therefore, after the upgrade, ChatGPT reclaimed its crown as the best AI chatbot. 

What is Gemini and how does it relate to ChatGPT?

Gemini is Google's AI chat service, a rival to ChatGPT. On February 6, 2023, Google introduced its experimental AI chat service, which was then called Google Bard. Over a month after the announcement, Google began rolling out  access to Bard first via a waitlist . Now, it is available to the general public. 

Artificial Intelligence

Chatgpt vs. copilot: which ai chatbot is better for you, how to use chatgpt (and how to access gpt-4o), what does gpt stand for understanding gpt-3.5, gpt-4, gpt-4o, and more.

Delving into PubMed Records: Some Terms in Medical Writing Have Drastically Changed after the Arrival of ChatGPT

• Find this author on Google Scholar
• Find this author on PubMed
• Search for this author on this site
• ORCID record for Kentaro Matsui
• For correspondence: [email protected]
• Info/History
• Supplementary material
• Preview PDF

It is estimated that ChatGPT is already widely used in academic paper writing. This study aims to investigate whether the usage of specific terminologies has increased, focusing on words and phrases frequently reported as overused by ChatGPT. The list of 118 potentially AI-influenced terms was curated based on posts and comments from anonymous ChatGPT users, and 75 common academic phrases were used as controls. PubMed records from 2000 to 2024 (until April) were analyzed to track the frequency of these terms. Usage trends were normalized using a modified Z-score transformation. A linear mixed-effects model was used to compare the usage of potentially AI-influenced terms to common academic phrases over time. A total of 26,403,493 PubMed records were investigated. Among the potentially AI-influenced terms, 75 displayed a meaningful increase (modified Z-score ≥ 3.5) in usage in 2024. The linear mixed-effects model showed a significant effect of potentially AI-influenced terms on usage frequency compared to common academic phrases (p < 0.001). The usage of potentially AI-influenced terms showed a noticeable increase starting in 2020. This study revealed that certain words and phrases, such as “delve,” “underscore,” “meticulous,” and “commendable,” have been used more frequently in medical and biological fields since the introduction of ChatGPT. The usage rate of these words/phrases has been increasing for several years before the release of ChatGPT, suggesting that ChatGPT might have accelerated the popularity of scientific expressions that were already gaining traction. The identified terms in this study can provide valuable insights for both LLM users, educators, and supervisors in these fields.

Author Summary Artificial intelligence systems have rapidly integrated into academic writing, particularly in the medical and biological fields. This study investigates changes in the frequency of specific terminologies reported as overused by ChatGPT. By analyzing PubMed records from 2000 to 2024, we tracked 118 potentially AI-influenced terms and compared them with 75 common academic phrases. The study’s findings reveal that terms such as ‘delve,’ ‘underscore,’ ‘meticulous,’ and ‘commendable’ saw a marked increase in usage in 2024. However, this trend actually began around 2020. This suggests that while some of these terms were already gaining popularity before the release of ChatGPT, the large language model may have accelerated their adoption in scientific literature. Furthermore, the analysis highlights that the impact of ChatGPT extends beyond new terminologies to altering the frequency and style of commonly used academic phrases. Understanding these trends can help researchers and educators see how AI tools are shaping academic writing.

Competing Interest Statement

The authors have declared no competing interest.

Funding Statement

KM is supported by the Japan Society for the Promotion of Science (JSPS) KAKENHI (grant number 22K15778).

Author Declarations

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Funding: KM is supported by the Japan Society for the Promotion of Science (JSPS) KAKENHI (grant number 22K15778).

Section on Possibly AI-influenced terms expanded with one additional entry; Abstract updated; Discussion section partially revised; Figures updated; Supplemental files updated.

Data Availability

The data used for the analysis was available as supplementary information (S3 Data).

View the discussion thread.

Supplementary Material

Thank you for your interest in spreading the word about medRxiv.

NOTE: Your email address is requested solely to identify you as the sender of this article.

Citation Manager Formats

• EndNote (tagged)
• EndNote 8 (xml)
• RefWorks Tagged
• Ref Manager
• Tweet Widget
• Facebook Like
• Google Plus One

Subject Area

• Health Informatics
• Addiction Medicine (325)
• Allergy and Immunology (633)
• Anesthesia (168)
• Cardiovascular Medicine (2409)
• Dentistry and Oral Medicine (291)
• Dermatology (208)
• Emergency Medicine (382)
• Endocrinology (including Diabetes Mellitus and Metabolic Disease) (854)
• Epidemiology (11817)
• Forensic Medicine (10)
• Gastroenterology (705)
• Genetic and Genomic Medicine (3782)
• Geriatric Medicine (351)
• Health Economics (638)
• Health Informatics (2415)
• Health Policy (941)
• Health Systems and Quality Improvement (909)
• Hematology (343)
• HIV/AIDS (790)
• Infectious Diseases (except HIV/AIDS) (13358)
• Intensive Care and Critical Care Medicine (770)
• Medical Education (371)
• Medical Ethics (105)
• Nephrology (403)
• Neurology (3536)
• Nursing (199)
• Nutrition (531)
• Obstetrics and Gynecology (683)
• Occupational and Environmental Health (671)
• Oncology (1839)
• Ophthalmology (541)
• Orthopedics (222)
• Otolaryngology (287)
• Pain Medicine (234)
• Palliative Medicine (67)
• Pathology (449)
• Pediatrics (1041)
• Pharmacology and Therapeutics (427)
• Primary Care Research (425)
• Psychiatry and Clinical Psychology (3204)
• Public and Global Health (6198)
• Radiology and Imaging (1298)
• Rehabilitation Medicine and Physical Therapy (753)
• Respiratory Medicine (833)
• Rheumatology (380)
• Sexual and Reproductive Health (375)
• Sports Medicine (325)
• Surgery (407)
• Toxicology (51)
• Transplantation (173)
• Urology (148)

Have a thesis expert improve your writing

Check your thesis for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• How to Write a Paper with ChatGPT | Tips & Examples

How to Write a Paper with ChatGPT | Tips & Examples

Published on 17 August 2023 by Koen Driessen .

A good research paper demonstrates your academic writing skills and knowledge of your chosen topic.

Your research paper should be based on in-depth independent research. However, generative AI tools like ChatGPT can be effectively used throughout the research process to:

• Brainstorm research questions
• Develop a methodology
• Create an outline
• Find sources
• Summarise and paraphrase text
• Provide feedback

Instantly correct all language mistakes in your text

Be assured that you'll submit flawless writing. Upload your document to correct all your mistakes.

Table of contents

Brainstorming research questions, developing a methodology, creating an outline, finding sources, summarising or paraphrasing text, receiving feedback, other interesting articles, frequently asked questions.

You can use ChatGPT to help formulate research questions , brainstorm potential thesis statements , or narrow down a broad subject area to a specific topic that interests you.

However, make sure that the outputs make sense and meet the requirements of your assignment. You can adapt these outputs manually, or use further prompts to ensure they meet your needs. For more information, see our tips for creating effective ChatGPT prompts .

• Generate three possible research questions for a research paper on the following topic: “The role of virtual reality in enhancing training and skill development in various industries.”
• “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods across different industries?”
• “How does the level of immersion in virtual reality training impact knowledge retention and skill transfer in fields such as medicine, aviation, and manufacturing?”
• “What are the key factors that influence the successful integration and adoption of virtual reality technology for training purposes in diverse industries, and what challenges hinder its widespread implementation?”

The only proofreading tool specialized in correcting academic writing

The academic proofreading tool has been trained on 1000s of academic texts and by native English editors. Making it the most accurate and reliable proofreading tool for students.

Correct my document today

Your paper should clearly indicate the data collection and analysis methods you used in your research.

You can use ChatGPT to help decide what kind of research you will conduct (e.g., qualitative or quantitative ), how you will analyse the data, and how you will mitigate potential research bias .

Bear in mind that you should be able to rationalize your chosen methodology . For example, you should ensure that it is either a standard methodology in the field or can be justified.

• Suggest three quantitative research methods appropriate to the following question: “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Experimental Study: Conduct a randomized controlled trial (RCT) where healthcare professionals are randomly assigned to either a virtual reality-based training group or a traditional training group. Both groups would receive training in specific healthcare tasks, and their cognitive and skill development outcomes would be measured and compared. Performance metrics, such as accuracy, speed, and efficiency, could be quantitatively assessed to determine the benefits of virtual reality-based training over traditional methods.
• Survey Research: Design a comprehensive survey targeting healthcare professionals who have undergone both virtual reality-based training and traditional training. The survey could include Likert-scale questions and structured response options to gauge their perceived cognitive and skill development benefits from each training method. Additionally, open-ended questions could be included to gather qualitative insights on specific strengths and weaknesses of each training approach.
• Task Performance Analysis: Implement a task-based assessment that simulates real-life healthcare scenarios, where participants are evaluated on their ability to handle critical situations. Participants would go through both virtual reality-based training and traditional training before being assessed in the simulated scenarios. Their performance in the assessment could be objectively measured using predefined criteria, allowing for a quantitative comparison of skill development between the two training methods.

A clear outline can help structure your paper, organise your arguments effectively, and make your research more efficient.

You can use generative AI tools like ChatGPT to formulate a potential outline to help guide your research. You can be as specific as you like, giving an overview of your research objectives , main arguments, and any evidence you intend to include in your paper.

However, ChatGPT outputs sometimes contain factual inaccuracies. It’s important to check the headings and subheadings suggested in the output and adapt them to meet your needs.

• Create an outline for an academic research paper with the following research question:“What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?” The paper will be about 10 pages long.

B. Existing studies on cognitive and skill development benefits of virtual reality training

C. Comparison of virtual reality-based training with traditional training methods

D. Gaps in the literature and research limitations

III. Theoretical Framework

A. Theoretical basis for cognitive and skill development in training

B. Application of cognitive theories to virtual reality-based training

C. The role of immersive learning environments in skill acquisition

D. Conceptual framework for the study

IV. Research Methodology

A. Research design and approach (e.g., quasi-experimental, pre-post intervention)

B. Selection of participants and sample size calculation

C. Description of the virtual reality-based training and traditional training programs

D. Instruments and measures for assessing cognitive and skill development

E. Data collection procedures and ethical considerations

V. Data Analysis

A. Overview of statistical methods used for data analysis

B. Treatment of data and data cleaning

C. Quantitative analysis of cognitive and skill development outcomes

D. Presentation of findings with charts and tables

VI. Results

A. Presentation of the results of the cognitive and skill development assessments

B. Comparison of outcomes between virtual reality-based training and traditional training

C. Statistical significance and effect size analysis

D. Interpretation of the results and implications

VII. Discussion

A. Interpretation of findings in the context of the research question

B. Comparison of results with existing literature

C. Explanation of how virtual reality-based training impacts cognitive processes and skill development

D. Limitations of the study and areas for future research

VIII. Practical Implications

A. Practical applications of virtual reality-based training in healthcare settings

B. Recommendations for integrating virtual reality training in healthcare education

C. Benefits of virtual reality for continuous professional development in healthcare

IX. Conclusion

A. Summary of key findings

B. Reiteration of the research question and hypothesis

C. Contributions of the study to the field of healthcare training

D. Concluding remarks

X. References

You can use ChatGPT to help find sources relevant to your research. However, it’s important to be aware of the limitations of ChatGPT (for example, it occasionally cites nonexistent sources).

Instead of asking ChatGPT for specific source recommendations, try asking it for recommendations on the types of sources relevant to your research topic. You can also use it to generate a list of relevant keywords to use in your literature search.

• What types of sources could I use to write a research paper on the following research question? “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Academic Journals: Peer-reviewed journals are valuable sources of scholarly research. Look for articles in medical education, cognitive psychology, virtual reality applications in healthcare, and technology-enhanced learning.
• Research Studies: Seek out published research studies that specifically investigate the impact of virtual reality-based training on cognitive and skill development in healthcare professionals.
• Systematic Reviews and Meta-Analyses: These studies provide comprehensive overviews of existing research on a specific topic, making them a valuable source for summarizing and analyzing the overall evidence.
• Books and Book Chapters: Academic books and book chapters authored by experts in the fields of medical education, virtual reality, cognitive science, or instructional design can provide in-depth insights and theoretical foundations.
• Conference Proceedings: Proceedings from relevant conferences and symposiums may present the latest findings and advancements in virtual reality-based training and healthcare education.
• Educational Institution Websites: Universities and medical schools often publish research papers, case studies, and whitepapers related to medical education and virtual reality training.
• Industry Reports: Reports and whitepapers from healthcare organizations or technology companies exploring the benefits of virtual reality-based training in the healthcare sector.
• Government and Non-profit Organisations: Look for reports and publications from government agencies and non-profit organisations that focus on medical education and healthcare training.
• Online Databases: Utilize academic databases such as PubMed, Google Scholar, IEEE Xplore, and ScienceDirect to search for peer-reviewed research articles and conference papers.
• Expert Interviews: If possible, conduct interviews with experts in medical education, cognitive science, and virtual reality to gain valuable insights and perspectives.
• Surveys and Polls: Refer to reputable surveys and polls related to virtual reality-based training in the healthcare industry for additional statistical data.

You can use ChatGPT to paraphrase or summarise text. This can help you to condense sources to their most important points and explore new ways of expressing your ideas.

Alternatively you can use the more specialised tools featured on Scribbr’s AI writing resources page, which are designed specifically for these purposes and will give a smoother user experience.

• Provide a short summary of the following text:“One of the most profound applications of VR in healthcare is its use in surgical training. Traditionally, surgical training has relied on a combination of didactic lectures, observation of procedures, and hands-on experience in the operating room. However, these methods may not provide the ideal environment for novices to develop the necessary dexterity and spatial understanding essential for complex surgeries. VR overcomes these limitations by offering immersive, true-to-life simulations that allow surgeons to navigate through intricate anatomical structures, practice incisions, and learn to manage unexpected challenges that may arise during surgeries. This hands-on experience in a risk-free environment not only enhances technical skills but also builds confidence and reduces the learning curve for new surgical techniques.”
• Virtual Reality (VR) has a profound impact on healthcare, particularly in surgical training, as it provides immersive simulations that help surgeons develop dexterity, spatial understanding, and confidence for complex surgeries in a risk-free environment, ultimately enhancing their technical skills and reducing the learning curve.

When you’ve finished writing your research paper, you can use ChatGPT to receive feedback. You can be as specific as you like, selecting particular aspects the output should focus on (e.g., tone, clarity of structure, appropriateness of evidence to support your arguments).

You can also use ChatGPT to check grammar, spelling, and punctuation. However, it’s not designed for this purpose and occasionally misses errors. We recommend using a more specialised tool like Scribbr’s free grammar checker . Or, for more comprehensive feedback, Scribbr’s proofreading and editing service .

• Feedback the above text with regard to appropriateness of evidence and coherence of structure.
• The research paper demonstrates a well-structured and coherent presentation of the cognitive and skill development benefits of VR-based surgical training. The introduction effectively sets the context and rationale, while the literature review incorporates relevant historical and empirical evidence. The theoretical framework strengthens the foundation for the analysis.The methodology section could provide more details on the research design and study selection criteria. However, the sections on cognitive and skill development benefits present compelling evidence, supported by appropriate sub-sections.The exploration of improved patient outcomes lacks concrete examples but effectively outlines potential benefits. The section on challenges and future directions raises relevant points, but suggestions for solutions could enhance practicality.Overall, the paper combines theoretical, empirical, and practical evidence, offering a well-rounded approach. It establishes the significance of VR-based surgical training and concludes with a concise summary of key findings.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, you can use ChatGPT to summarise text . This can help you understand complex information more easily, summarise the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summariser , which is designed specifically for this purpose.

Yes, you can use ChatGPT to paraphrase text to help you express your ideas more clearly, explore different ways of phrasing your arguments, and avoid repetition.

However, it’s not specifically designed for this purpose. We recommend using a specialised tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

No, having ChatGPT write your college essay can negatively impact your application in numerous ways. ChatGPT outputs are unoriginal and lack personal insight.

Furthermore, Passing off AI-generated text as your own work is considered academically dishonest . AI detectors may be used to detect this offense, and it’s highly unlikely that any university will accept you if you are caught submitting an AI-generated admission essay.

However, you can use ChatGPT to help write your college essay during the preparation and revision stages (e.g., for brainstorming ideas and generating feedback).

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

Driessen, K. (2023, August 17). How to Write a Paper with ChatGPT | Tips & Examples. Scribbr. Retrieved 30 May 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-paper/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, chatgpt citations | formats & examples, ethical implications of chatgpt, still have questions.