how to write literature review with ai

AI Literature Review Generator

Generate high-quality literature reviews fast with ai.

• Academic Research: Create a literature review for your thesis, dissertation, or research paper.
• Professional Research: Conduct a literature review for a project, report, or proposal at work.
• Content Creation: Write a literature review for a blog post, article, or book.
• Personal Research: Conduct a literature review to deepen your understanding of a topic of interest.

New & Trending Tools

In-cite ai reference generator, legal text refiner, job search ai assistant.

Revolutionize Your Research with Jenni AI

Literature Review Generator

Welcome to Jenni AI, the ultimate tool for researchers and students. Our AI Literature Review Generator is designed to assist you in creating comprehensive, high-quality literature reviews, enhancing your academic and research endeavors. Say goodbye to writer's block and hello to seamless, efficient literature review creation.

Loved by over 1 million academics

Endorsed by Academics from Leading Institutions

Join the Community of Scholars Who Trust Jenni AI

Elevate Your Research Toolkit

Discover the Game-Changing Features of Jenni AI for Literature Reviews

Advanced AI Algorithms

Jenni AI utilizes cutting-edge AI technology to analyze and suggest relevant literature, helping you stay on top of current research trends.

Get started

Idea Generation

Overcome writer's block with AI-generated prompts and ideas that align with your research topic, helping to expand and deepen your review.

Citation Assistance

Get help with proper citation formats to maintain academic integrity and attribute sources correctly.

Our Pledge to Academic Integrity

At Jenni AI, we are deeply committed to the principles of academic integrity. We understand the importance of honesty, transparency, and ethical conduct in the academic community. Our tool is designed not just to assist in your research, but to do so in a way that respects and upholds these fundamental values.

How it Works

Start by creating your account on Jenni AI. The sign-up process is quick and user-friendly.

Define Your Research Scope

Enter the topic of your literature review to guide Jenni AI’s focus.

Citation Guidance

Receive assistance in citing sources correctly, maintaining the academic standard.

Easy Export

Export your literature review to LaTeX, HTML, or .docx formats

Interact with AI-Powered Suggestions

Use Jenni AI’s suggestions to structure your literature review, organizing it into coherent sections.

What Our Users Say

Discover how Jenni AI has made a difference in the lives of academics just like you

· Aug 26

I thought AI writing was useless. Then I found Jenni AI, the AI-powered assistant for academic writing. It turned out to be much more advanced than I ever could have imagined. Jenni AI = ChatGPT x 10.

Charlie Cuddy

@sonofgorkhali

· 23 Aug

Love this use of AI to assist with, not replace, writing! Keep crushing it @Davidjpark96 💪

Waqar Younas, PhD

@waqaryofficial

· 6 Apr

4/9 Jenni AI's Outline Builder is a game-changer for organizing your thoughts and structuring your content. Create detailed outlines effortlessly, ensuring your writing is clear and coherent. #OutlineBuilder #WritingTools #JenniAI

I started with Jenni-who & Jenni-what. But now I can't write without Jenni. I love Jenni AI and am amazed to see how far Jenni has come. Kudos to http://Jenni.AI team.

· 28 Jul

Jenni is perfect for writing research docs, SOPs, study projects presentations 👌🏽

Stéphane Prud'homme

http://jenni.ai is awesome and super useful! thanks to @Davidjpark96 and @whoisjenniai fyi @Phd_jeu @DoctoralStories @WriteThatPhD

Frequently asked questions

What exactly does jenni ai do, is jenni ai suitable for all academic disciplines, is there a trial period or a free version available.

How does Jenni AI help with writer's block?

Can Jenni AI write my literature review for me?

How often is the literature database updated in Jenni AI?

How user-friendly is Jenni AI for those not familiar with AI tools?

Jenni AI: Standing Out From the Competition

In a sea of online proofreaders, Jenni AI stands out. Here’s how we compare to other tools on the market:

Feature Featire

COMPETITORS

Advanced AI-Powered Assistance

Uses state-of-the-art AI technology to provide relevant literature suggestions and structural guidance.

May rely on simpler algorithms, resulting in less dynamic or comprehensive support.

User-Friendly Interface

Designed for ease of use, making it accessible for users with varying levels of tech proficiency.

Interfaces can be complex or less intuitive, posing a challenge for some users.

Transparent and Flexible Pricing

Offers a free trial and clear, flexible pricing plans suitable for different needs.

Pricing structures can be opaque or inflexible, with fewer user options.

Unparalleled Customization

Offers highly personalized suggestions and adapts to your specific research needs over time.

Often provide generic suggestions that may not align closely with individual research topics.

Comprehensive Literature Access

Provides access to a vast and up-to-date range of academic literature, ensuring comprehensive research coverage.

Some may have limited access to current or diverse research materials, restricting the scope of literature reviews.

Ready to Transform Your Research Process?

Don't wait to elevate your research. Sign up for Jenni AI today and discover a smarter, more efficient way to handle your academic literature reviews.

How To Use Elicit For Literature Review: AI Research Assistant 101

Navigating the vast sea of academic research can be daunting. Fortunately, Elicit, an advanced AI-driven tool, offers a streamlined solution for conducting comprehensive literature reviews.

 This article will guide you through the step-by-step process of using Elicit to efficiently locate, analyse, and organise relevant research papers.

Whether you’re a seasoned academic or a novice researcher, understanding how to leverage Elicit’s capabilities can significantly enhance your research efficiency and effectiveness. Let’s dive into how you can make the most of this powerful tool.

How To Use Elicit For Literature Review

What is elicit ai (elicit.org).

Elicit is an AI research assistant revolutionising the way you perform literature review research. At its core, Elicit.org allows you to automate parts of the research process that traditionally consumed hours.

When you use Elicit, you start by entering a specific research question.

The system uses advanced AI to filter through millions of research articles, showing relevant papers and summaries of key information about those papers in an easy-to-use format. 

Elicit’s capabilities extend to refining search results by:

• citation count, or
• study type,

which is particularly useful for conducting a systematic review. You can even see the number of citations a paper has received, helping gauge its impact and relevance. 

Plus, the tool offers options to export data in a CSV or bib file, integrating smoothly with reference managers like Zotero, which is a boon for maintaining academic integrity.

What sets Elicit apart is its mission to automate and scale your research workflow. Whether you’re behind academia’s paywalls or exploring open access, Elicit navigates the terrain, ensuring you don’t overlook any critical piece of literature.

This makes your literature review process not only faster but also more exhaustive, leaving you free to focus on synthesis and analysis rather than the mechanics of the literature search.

Steps To Use Elicit For Literature Review

If you are looking for a simple step-by-step guide to use Elicit for literature review, here’s a guide for you to start with: 

Step 1: Start with a Specific Research Question

When you log into Elicit.org, you’ll be prompted to enter a research question. This should be as specific as possible to ensure the results are directly relevant to your study.

If you’re interested in how virtual reality affects learning outcomes, your query could be “What are the impacts of virtual reality on student engagement and learning outcomes in higher education?”

Step 2: Review the Search Results

Once you submit your question, Elicit utilises AI to sift through vast databases, displaying research papers that align with your query.

The results are presented with:

• abstract summaries, and
• the number of citations,

helping you gauge the relevance and influence of each study at a glance.

Step 3: Use Filters to Refine Your Search

Elicit provides various filters to refine your results further. You can filter papers by:

• publication date,
• study type, or
• the number of citations.

This functionality is particularly helpful if you’re conducting a systematic review and need to adhere to specific criteria.

Step 4: Analyse Abstract Summaries

The abstract summaries provided by Elicit are generated using AI, offering a concise overview of each paper. You can quickly scan through to see if there are any papers that may be relevant to your work.

While these summaries are useful for quick scans, it’s crucial to access the full papers for a thorough review, ensuring the AI’s interpretation aligns with the actual content.

Step 5: Dive Deeper into Selected Papers

For papers that seem particularly relevant, click on them to see more detailed information. Elicit allows you to:

• read the full abstract,
• check the paper’s citation history, and
• view any available PDFs.

This step is vital for understanding the context and methodology of the research, ensuring it fits your review’s scope.

Step 6: Export Data for Easy Access

You can export the data you find useful directly from Elicit in formats like CSV or BibTeX, which can be imported into reference management tools like Zotero.

This feature supports maintaining an organised and accessible bibliography and references, essential for academic integrity.

Step 7: “Star” Relevant Papers

As you comb through the search results, you might find papers that warrant closer examination later. Elicit’s “star” feature allows you to bookmark these papers.

You can easily access your starred list at any point, which helps in structuring your literature review and ensuring no critical research is overlooked.

Step 8: Adjust Your Query as Needed

Based on the papers you find, you might discover new keywords or concepts to explore. Elicit allows you to modify your search terms in real-time, dynamically adjusting the displayed results.

This iterative process helps you hone in on the most pertinent information. Feel free to use this features until you have found what you needed.

Step 9: Utilize Elicit’s Additional Features

Elicit also offers advanced features like suggesting related research questions or identifying methodological critiques within studies.

These insights can provide new directions for your review or highlight potential limitations in existing research.

Step 10: Continuously Update Your Review

Literature reviews are often ongoing projects, especially in fast-evolving fields. Fortunately, Elicit can help you keep up with this.

Elicit’s user-friendly interface and real-time data updates make it easy to add new research as it becomes available, ensuring your review remains current and comprehensive.

Use AI Tools For Academic Work

By leveraging Elicit’s capabilities, you can significantly reduce the time and effort typically required for literature searches.

This AI-driven tool not only streamlines finding relevant papers but also enhances your ability to analyse and synthesise key information effectively. 

With Elicit as your research assistant, you’re well-equipped to undertake even the most complex literature reviews, making your research process more systematic and efficient. 

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

Accelerate your dissertation literature review with AI

Become a lateral pioneer.

Get started for free and help craft the future of research.

Early access. No credit card required.

Introduction

Dissertation writing is part of being a graduate student. There are many different ways to organise your research, and several steps to this process . Typically, the literature review is an early chapter in the dissertation, providing an overview of the field of study. It should summarise relevant research papers and other materials in your field, with specific references. To understand how to write a good literature review, we must first understand its purpose. The goals of a literature review are to place your dissertation topic in the context of existing work (this also allows you to acknowledge prior contributions, and avoid accusations of plagiarism), and to set you up to show you are making a new contribution to the field. Since literature review is repetitive, many students find it tedious. While there are some traditional tools and techniques to help, covered below, they tend to be cumbersome and keyword-based. For this reason, we built a better tool for research and literature review, which I describe in the last section. You can see the Lateral tool in action , and how it makes the literature review a lot easier. To sign up to the tool, click here.

1. Different kinds of reading

We can divide the activity of reading for research into three different kinds: 

• Exploratory reading, mostly done in the initial phase;
• Deep reading of highly informative sources; and 
• Broad, targeted skim reading of large collections of books and articles, in order to find specific kinds of information you already know exist.

1.1. Exploratory reading

Initially, a research student will need to read widely in a new field to gain fundamental understanding. In this early stage, the goal is to explore and digest the main ideas in existing research. Traditionally, this phase has been a manual process, but there is a new generation of digital tools to aid in getting a quick overview of your field, and more generally to organise your research . This stage can happen both before and after the research topic or question has been formulated. It is often unstructured and full of serendipitous (“happy accidental”) discovery  — the student’s job is to absorb what they find, rather than to conduct a targeted search for particular information. ‍

Put another way: You don’t know what you’re looking for ahead of time. By the end of this phase, you should be able to sketch a rough map of your field of study.

1.2. Narrow, deep reading

After the exploratory reading phase, you will be able to prioritise the information you read. Now comes the second phase: Deep, reflective reading. In this phase, your focus will narrow to a small number of highly relevant sources — perhaps one or two books, or a handful of articles — which you will read carefully, with the goal of fully understanding important concepts. This is a deliberative style of reading, often accompanied by reflective pauses and significant note taking. If the goal in the first phase was sketching a map of the globe, the goal in this second phase is to decide which cities interest you most, and map them out in colour and detail.

1.3. Broad, targeted reading

You have now sketched a map of your field of study (exploratory reading), and filled in some parts of this map in more detail (narrow, deep reading). I will assume that by this point, you have found a thesis question or research topic, either on your own, or with the help of an advisor. This is often where the literature review begins in earnest. In order to coherently summarise the state of your field, you must review the literature once again, but this time in a more targeted way: You are searching for particular pieces of information that either illustrate existing work, or demonstrate a need for the new approach you will take in your dissertation. For example, 

• You want to find all “methodology” sections in a group of academic articles, and filter for those that have certain key concepts;
• You want to find all paragraphs that discuss product-market fit, inside a group of academic articles.

To return to the map analogy: This is like sketching in the important roads between your favourite cities — you are showing connections between the most important concepts in your field, through targeted information search.

2. Drawbacks of broad targeted reading

The third phase — broad, targeted reading, where you know what kind of information you’re looking for and simply wish to scan a collection of articles or books to find it — is often the most mechanical and time consuming one. Since human brains tend to lose focus in the face of dull repetition, this is also a tedious and error-prone phase for many people. What if you miss something important because you’re on autopilot? Often, students end up speed- or skim reading through large volumes of information to complete the literature review as quickly as possible. With focus and training, this manual approach can be efficient and effective, but it can also mean reduced attention to detail and missed opportunities to discover relevant information. Only half paying attention during this phase can also lead to accidental plagiarism, otherwise known as cryptomnesia: Your brain subconsciously stores a distinctive idea or quote from the existing literature without consciously attributing it to its source reference. Afterwards, you end up falsely, but sincerely believing you created the idea independently, exposing yourself to plagiarism accusations.

3. Existing solutions to speed up literature reviews

Given the drawbacks of manual speed- or skim-reading in the broad reading phase, it’s natural to turn to computer-driven solutions. One popular option is to systematically create a list of search term keywords or key phrases, which can then be combined using boolean operators to broaden results. For example, in researching a study about teenage obesity, one might use the query:

• “BMI” or “obesity” and “adolescents” and not “geriatric”,

to filter for obesity-related articles that do mention adolescents, but don’t mention older adults.

Constructing such lists can help surface many relevant articles, but there are some disadvantages to this strategy:

• These keyword queries are themselves fiddly and time-consuming to create.
• Often what you want to find is whole “chunks” of text — paragraphs or sections, for example — not just keywords.
• Even once you have finished creating your boolean keyword query list, how do you know you haven’t forgotten to include an important search query?

This last point reflects the fact that keyword searching is “fragile” and error-prone: You can miss results that would be relevant — this is known as getting “false negatives” — because your query uses words that are similar, but not identical to words appearing in one or more articles in the library database. For example, the query “sporting excellence” would not match with an article that mentioned only “high performance athletics”.

4. Lateral — a new solution

To make the process of finding specific information in big collections of documents quicker and easier — for example, in a literature review — search, we created the Lateral app , a new kind of AI-driven interface to help you organise, search through and save supporting quotes and information from collections of articles. Using techniques from natural language processing, it understands, out-of-the-box, not only that “sporting excellence” and “high-performance” athletics are very similar phrases, but also that two paragraphs discussing these topics in slightly different language are likely related. Moreover, it also learns to find specific blocks of information, given only a few examples. Want to find all “methodology” sections in a group of articles? Check. How about all paragraphs that mention pharmaceutical applications? We have you covered. If you’re interested, you can sign up today .

5. Final note — novel research alongside the literature review

Some students, to be more efficient, use the literature review process to collect data not just to summarise existing work, but also to support one or more novel theses contained in their research topic. After all, you are reading the literature anyway, so why not take the opportunity to note, for example, relevant facts, quotes and supporting evidence for your thesis? Because Lateral is designed to learn from whatever kind of information you’re seeking, this process also fits naturally into the software’s workflow.

References:

• Is your brain asleep on the job?: https://www.psychologytoday.com/us/blog/prime-your-gray-cells/201107/is-your-brain-asleep-the-job
• Tim Feriss speed reading: https://www.youtube.com/watch?v=ZwEquW_Yij0
• Five biggest reading mistakes: https://www.timeshighereducation.com/blog/five-biggest-reading-mistakes-and-how-avoid-them
• Skim reading can be bad: https://www.inc.com/jeff-steen/why-summaries-skim-reading-might-be-hurting-your-bottom-line.html
• Cryptomnesia: https://en.wikipedia.org/wiki/Cryptomnesia
• Systematic literature review with boolean keywords: https://libguides.library.cqu.edu.au/c.php?g=842872&p=6024187

Lit review youtube intro: https://www.youtube.com/watch?v=bNIG4qLuhJA

Spread the word

There is a better way than Dropbox and Google Drive to do collaborative research

In this blog, I describe the limitations of Dropbox and Google in the space of research, and propose Lateral as the much needed alternative.

Remote group work and the best student collaboration tools

In this blog, I outline some organisational techniques and the best digital collaborative tools for successful student group work.

6 things to consider and organise before writing your dissertation (and how Lateral can help)

I hope the following six things to consider and organise will make the complex dissertation writing more manageable.

Get into flow.

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
• CAREER FEATURE
• 04 December 2020
• Correction 09 December 2020

How to write a superb literature review

Andy Tay is a freelance writer based in Singapore.

You can also search for this author in PubMed   Google Scholar

Literature reviews are important resources for scientists. They provide historical context for a field while offering opinions on its future trajectory. Creating them can provide inspiration for one’s own research, as well as some practice in writing. But few scientists are trained in how to write a review — or in what constitutes an excellent one. Even picking the appropriate software to use can be an involved decision (see ‘Tools and techniques’). So Nature asked editors and working scientists with well-cited reviews for their tips.

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

doi: https://doi.org/10.1038/d41586-020-03422-x

Interviews have been edited for length and clarity.

Updates & Corrections

Correction 09 December 2020 : An earlier version of the tables in this article included some incorrect details about the programs Zotero, Endnote and Manubot. These have now been corrected.

Hsing, I.-M., Xu, Y. & Zhao, W. Electroanalysis 19 , 755–768 (2007).

Article   Google Scholar  

Ledesma, H. A. et al. Nature Nanotechnol. 14 , 645–657 (2019).

Article   PubMed   Google Scholar  

Brahlek, M., Koirala, N., Bansal, N. & Oh, S. Solid State Commun. 215–216 , 54–62 (2015).

Choi, Y. & Lee, S. Y. Nature Rev. Chem . https://doi.org/10.1038/s41570-020-00221-w (2020).

Download references

Related Articles

• Research management

How religious scientists balance work and faith

Career Feature 20 MAY 24

How to set up your new lab space

Career Column 20 MAY 24

I’m worried I’ve been contacted by a predatory publisher — how do I find out?

Career Feature 15 MAY 24

US halts funding to controversial virus-hunting group: what researchers think

News 16 MAY 24

Japan can embrace open science — but flexible approaches are key

Correspondence 07 MAY 24

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

Career Feature 08 MAY 24

Mount Etna’s spectacular smoke rings and more — April’s best science images

News 03 MAY 24

Senior Postdoctoral Research Fellow

Senior Postdoctoral Research Fellow required to lead exciting projects in Cancer Cell Cycle Biology and Cancer Epigenetics.

Melbourne University, Melbourne (AU)

University of Melbourne & Peter MacCallum Cancer Centre

Overseas Talent, Embarking on a New Journey Together at Tianjin University

We cordially invite outstanding young individuals from overseas to apply for the Excellent Young Scientists Fund Program (Overseas).

Tianjin, China

Tianjin University (TJU)

Chair Professor Positions in the School of Pharmaceutical Science and Technology

SPST seeks top Faculty scholars in Pharmaceutical Sciences.

Chair Professor Positions in the School of Precision Instruments and Optoelectronic Engineering

We are committed to accomplishing the mission of achieving a world-top-class engineering school.

Chair Professor Positions in the School of Mechanical Engineering

Aims to cultivate top talents, train a top-ranking faculty team, construct first-class disciplines and foster a favorable academic environment.

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

• How to Ethically Write Your Literature Review Using AI: A Comprehensive Guide

by Laura Perez | Mar 17, 2024 | Uncategorized | 1 comment

This traditional method, while thorough, was fraught with inefficiencies and obstacles. The most poignant of these was perhaps the sheer volume of time consumed in the pursuit of academic rigour, a precious resource that could scarcely be afforded by many. Moreover, the manual nature of the process introduced a higher risk of oversight and error, potentially compromising the precision and accuracy so vital to scholarly work.

Fast forward to the present, and the landscape of academic research has been transformed irrevocably by the advent of artificial intelligence (AI). What once took months, or even years, can now be accomplished in a matter of weeks, thanks to the automation capabilities of AI technologies. The literature review process, in particular, has been revolutionised. AI-powered tools such as ChatGPT have not only streamlined the discovery and analysis of relevant literature but have also enhanced the accuracy and precision of these reviews. No longer must researchers endure the tedium of sifting through irrelevant papers or the monotony of writing reviews of others’ work. Instead, AI enables a focus on the essence of research—generating insights and contributing to the body of knowledge with efficiency and ease.

This seismic shift has not only expedited the research process but has also opened new avenues for exploration, allowing scholars to delve deeper into their subjects with the support of AI’s vast computational power and intelligent analysis. The result? A literature review that is not only quicker to compile but richer in insight and more robust in its scholarly contribution. As we stand on the threshold of this new era in academic research, it’s clear that AI has not just changed the game—it’s redefined it.

This guide is crafted to delineate how one can ethically utilise ChatGPT to automate aspects of literature review, ensuring that the process remains within the ethical boundaries set by academia.

Embarking on Your Literature Review with a Clear Question

The foundation of a solid literature review is a well-crafted research question. This query should strike a balance, being narrow enough to be manageable, yet broad enough to encompass the complexity of your topic. ChatGPT can play a pivotal role here, aiding in refining your ideas into a polished research question by offering suggestions based on the existing body of knowledge and identified research gaps.

Creating a Structured Outline with ChatGPT’s Help

With your research question in hand, the next step is to draft a detailed outline for your literature review, and here’s where ChatGPT comes into play:

• Identifying Key Themes : ChatGPT can assist in brainstorming relevant themes and subtopics, ensuring your review covers all necessary ground.
• Organising the Structure : The AI can recommend a logical flow for these themes, enhancing the coherence of your review.
• Refining Sections : ChatGPT can further refine your outline, suggesting where to expand or narrow down sections to align with your research question.

Efficient Research with Google Scholar

With an outline ready, Google Scholar becomes your go-to for sourcing high-quality academic papers, articles, and books. Keywords extracted from your outline, facilitated by ChatGPT, direct your searches, while abstracts give quick insights into each document’s relevance.

Streamlining References with Zotero

Zotero, a free reference management tool, is invaluable for keeping track of your sources. It simplifies citation and reference organisation, crucial for maintaining academic integrity. Zotero integrates seamlessly into your research workflow, from browser extensions for easy source collection to facilitating in-text citations and bibliographies in your document.

Building a Compelling Argument with the PIER System

To structure your literature review effectively, consider the PIER system:

• Point : Start sections with a statement that addresses your research question.
• Integration of Evidence : Use evidence from your sources to back up each point.
• Examples for Support : Illustrate your arguments with specific findings from your research.
• Recap : Conclude sections with summaries that tie back to your main question.

Refining Your Draft with ChatGPT

ChatGPT becomes a valuable asset again in the drafting phase, offering initial feedback on argument strength, coherence, and areas needing more evidence. Critically evaluate ChatGPT’s suggestions to ensure they align with your research objectives.

Ethical AI Use: A Success Story

One student’s experience highlights the transformative potential of ethically using ChatGPT for literature reviews. By leveraging AI, the student not only expedited their review process but also enriched the analytical depth of their work, resulting in significant academic improvement.

In Conclusion

The ethical employment of AI in academic research, especially in the drafting of literature reviews, marries the efficiency of technology with the researcher’s critical thinking skills. Following this guide ensures you can benefit from AI like ChatGPT, from formulating research questions to refining your final draft, all while adhering to the highest ethical standards.

Your blog is a testament to your dedication to your craft. Your commitment to excellence is evident in every aspect of your writing. Thank you for being such a positive influence in the online community.

Don’t forget to follow us :)

Recent Posts

• Does it really need to take 3 or 4 years to complete a Ph.D. in 2024?
• Understanding the Role of Accrediting Agencies in Ensuring Quality Education
• New “Peacemaker” Master’s Degree Programme
• Best FREE AI Tools for Academic Research and Researchers in 2024

Powered by WhatsApp Chat

WhatsApp Chat is free, download and try it now here!

Literature Reviews

• Artificial intelligence (AI) tools
• Getting started
• Types of reviews
• 1. Define your research question
• 2. Plan your search
• 3. Search the literature
• 4. Organize your results
• 5. Synthesize your findings
• 6. Write the review

Introduction to AI

Research rabbit, copilot (powered by chatgpt4).

• Thompson Writing Studio This link opens in a new window
• Need to write a systematic review? This link opens in a new window

Contact a Librarian

Ask a Librarian

Generative AI tools have been receiving a lot of attention lately because they can create content like text, images, and music. These tools employ machine learning algorithms that can produce unique and sometimes unexpected results. Generative AI has opened up exciting possibilities in different fields, such as language models like GPT and image generators.

However, students need to approach these tools with awareness and responsibility. Here are some key points to consider:

Novelty and Creativity : Generative AI tools can produce content that is both innovative and unexpected. They allow users to explore new ideas, generate unique artworks, and even compose original music. This novelty is one of their most exciting aspects.

Ethical Considerations : While generative AI offers creative potential, it also raises ethical questions. Students should be aware of potential biases, unintended consequences, and the impact of their generated content. Responsible use involves considering the broader implications.

Academic Integrity : When using generative AI tools for academic purposes, students should consult their instructors. Policies regarding the use of AI-generated content may vary across institutions. Always seek guidance to ensure compliance with academic integrity standards.

In summary, generative AI tools are powerful and fascinating, but students should approach them thoughtfully, seek guidance, and adhere to institutional policies. Please refer to the Duke Community Standard  for questions related to ethical AI use.

Looking for a tool that isn't listed here? Let us know about it!

Research Rabbit is a literature mapping tool that takes one paper and performs backward- and forward citation searching in addition to recommending "similar work." It scans the Web for publicly available content to build its "database" of work.

Best suited for...

Disciplines whose literature is primarily published in academic journals.

Considerations

• Integrates with Zotero
• Works mostly with just journal articles
• Potential for bias in citation searching/mapping

»   researchrabbit.ai   «

What is it?

Elicit is a tool that semi-automates time-intensive research processes, such as summarizing papers , extracting data , and synthesizing information . Elicit pulls academic literature from Semantic Scholar , an academic search engine that also uses machine learning to summarize information.

Empirical research (i.g., the sciences, especially biomedicine).

• Both free and paid versions
• Doesn't work well in identifying facts or in theoretical/non-empirical research (e.g., the humanities)
• Potential biases in the natural language processing (NLP) algorithms
• Summarized information and extracted data will still need to be critically analyzed and verified for accuracy by the user

»   elicit.com   «

Think of Consensus as ChatGPT for research! Consensus is "an AI-powered search engine designed to take in research questions, find relevant insights within research papers, and synthesize the results using the power of large language models" ( Consensus.app ).  Consensus runs its language model over its entire body of scientific literature (which is sourced from Semantic Scholar ) and extracts the “key takeaway” from every paper.

The social sciences and sciences (non-theoretical disciplines).

• Free and paid versions
• Similar to Elicit, Consensus should not be used to ask questions about basic facts
• Consensus recommends that you ask questions related to research that has already been conducted by scientists
• Potential for biases in the input data from participants

»   consensus.app   «

Dubbed the "AI-powered Swiss Army Knife for information discovery," Perplexity is used for answering questions (including basic facts, a function that many other AI tools are not adept at doing), exploring topics in depth utilizing Microsoft's Copilot, organizing your research into a library, and interacting with your data (including asking questions about your files).

Perplexity has wide-reaching applications and could be useful across disciplines.

• Free and paid pro versions (the pro version utilizes Microsoft's Copilot AI tool)
• Available in desktop, iOS, and Android apps
• See  Perplexity's blog for more info
• Your personal information and data on how you use the tool are stored for analytical purposes (however, this feature can be turned off in settings)
• Features a browser plug-in, Perplexity Companion , that is essentially a blend of Google and ChatGPT

»   perplexity.ai   «

Did you know that as Duke faculty, staff, and students, we have free access to ChatGPT4 via Microsoft Copilot ?

Log in with your Duke credentials to start using it today.

The OG of generative AI tools, ChatGPT-4 is the latest iteration of the popular chatbot, answering questions and generating text that sounds like it was written by a human. While not a replacement for conducting research, it can be helpful when it comes to brainstorming topics or research questions and also as a writing tool (rewriting or paraphrasing content, assessing tone, etc.).

All users across all disciplines.

• ChatGPT-3.5 is the default version of free and paid-tier chat users.
• Since it can't verify its sources, be wary of hallucinations (or made-up citations) that can look very real.
• It is not 100% accurate ! While ChatGPT-4 is touted as being 40% more accurate than its predecessor, users are still expected to verify the information generated by it.
• There is always the potential for bias since ChatGPT was trained on a massive dataset of websites, articles, books, etc. (much of which is inherently biased since it was created by humans).

For ChatGPT-4 (access provided by Duke and requires login) »   copilot.microsoft.com   «

For ChatGPT-3.5 (free) »   chat.openai.com   «

• << Previous: 6. Write the review
• Next: Thompson Writing Studio >>
• Last Updated: May 17, 2024 8:42 AM
• URL: https://guides.library.duke.edu/litreviews

Services for...

• Faculty & Instructors
• Graduate Students
• Undergraduate Students
• International Students
• Patrons with Disabilities

• Harmful Language Statement
• Re-use & Attribution / Privacy
• Support the Libraries

• Research Guides
• University Libraries

AI-Based Literature Review Tools

• Dialogues: Insightful Facts
• How to Craft Prompts
• Plugins / Extensions for AI-powered Searches
• Cite ChatGPT in APA / MLA
• AI and Plagiarism
• ChatGPT & Higher Education
• Author Profile

Selected AI-Based Literature Review Tools

Updates: See news or release of AI (Beta) across various academic research databases including Web of Science , Scopus , Ebsco , ProQues t, OVID , Dimensions , JStor , Westlaw , and LexisNexis . ********* ********** ********** ********** **********   

Disclaimer: TAMU libraries do not have subscription access to the AI-powered tools listed below the divider line. The guide serves solely as an informational resource. It is recommended that you assess these tools and their usage methodologies independently. ------------------------------------------------------------------------------------------------------------------------------------------------------------- SEMANTIC SCHOLAR

• SCIENTIFIC LITERATURE SEARCH ENGINE - finding semantically similar research papers.
• " A free, AI-powered research tool for scientific literature."  <https://www.semanticscholar.org/>. But login is required in order to use all functions.
• Over 200 millions of papers from all fields of science, the data of which has also served as a wellspring for the development of other AI-driven tools.

The 4000+ results can be sorted by Fields of Study, Date Range, Author, Journals & Conferences

Save the papers in your Library folder. The Research Feeds will recommend similar papers based on the items saved.

Example - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality Total Citations: 22,438   [Note: these numbers were gathered when this guide was created] Highly Influential Citations 2,001 Background Citations 6,109 Methods Citations 3,273  Results Citations 385

TLDRs (Too Long; Didn't Read) Try this example . Press the pen icon to reveal the highlighted key points . TLDRs "are super-short summaries of the main objective and results of a scientific paper generated using expert background knowledge and the latest GPT-3 style NLP techniques. This new feature is available in beta for nearly 60 million papers in computer science, biology, and medicine..." < https://www.semanticscholar.org/product/tldr>

• https://www.openread.academy/
• Institutionally accessed by Harvard, MIT, University of Oxford, Johns Hopkins, Standford, Beijing University. .
• AI-powered Academic Searching + Web Searching - Over 300 million papers and real-time web content.
• Every keyword search or AI quest will yield a synthesis report with citations. If you want to re-orient the search outcomes, just click on the Re-generate button and all citations will be refreshed accordingly. After that click on Follow-Up Questions to delve deeper into a particular area or subject.
• Use Paper Q&A to interact with a text directly, e.g. " What does this paper say about literature review ?"
• Click on the Translation to put a text or search results into another language.
• Upload a PDF document and let Paper Expresso to read it for you and parse the content into an academic report format for easy screening: Background and context> Research objectives and hypotheses> Methodology> Results and findings> Discussion and interpretation> Contributions to the field > Structure and flow> Achievements and significance> Limitations and future work>
• AI-POWERED RESEARCH ASSISTANT - finding papers, filtering study types, automating research flow, brainstorming, summarizing and more.
• " Elicit is a research assistant using language models like GPT-3 to automate parts of researchers’ workflows. Currently, the main workflow in Elicit is Literature Review. If you ask a question, Elicit will show relevant papers and summaries of key information about those papers in an easy-to-use table."   <https://elicit.org/faq#what-is-elicit.>; Find answers from 175 million papers. FAQS
• Example - How do mental health interventions vary by age group?    /   Fish oil and depression Results: [Login required] (1) Summary of top 4 papers > Paper #1 - #4 with Title, abstract, citations, DOI, and pdf (2) Table view: Abstract / Interventions / Outcomes measured / Number of participants (3) Relevant studies and citations. (4) Click on Search for Paper Information to find - Metadata about Sources ( SJR etc.) >Population ( age etc.) >Intervention ( duration etc.) > Results ( outcome, limitations etc.) and > Methodology (detailed study design etc.) (5) Export as BIB or CSV
• How to Search / Extract Data / List of Concept Search -Enter a research question >Workflow: Searching > Summarizing 8 papers> A summary of 4 top papers > Final answers. Each result will show its citation counts, DOI, and a full-text link to Semantic Scholar website for more information such as background citations, methods citation, related papers and more. - List of Concepts search - e.g. adult learning motivation . The results will present a list the related concepts. - Extract data from a pdf file - Upload a paper and let Elicit extract data for you.
• Export Results - Various ways to export results.
• How to Cite - Includes the elicit.org URL in the citation, for example: Ought; Elicit: The AI Research Assistant; https://elicit.org; accessed xxxx/xx/xx

CONSENSUS.APP

ACADEMIC SEARCH ENGINE- using AI to find insights in research papers.

"We are a search engine that is designed to accept research questions, find relevant answers within research papers, and synthesize the results using the same language model technology." <https://consensus.app/home/blog/maximize-your-consensus-experience-with-these-best-practices/>

• Example - Does the death penalty reduce the crime?   /  Fish oil and depression  /    (1) Extracted & aggregated findings from relevant papers. (2) Results may include AIMS, DESIGN, PARTICIPANTS, FINDINGS or other methodological or report components. (3) Summaries and Full Text
• How to Search Direct questions - Does the death penalty reduce the crime? Relationship between two concepts - Fish oil and depression / Does X cause Y? Open-ended concepts - effects of immigration on local economics Tips and search examples from Consensus' Best Practice   
• Synthesize (beta) / Consensus Meter When the AI recognizes certain types of research questions, this functionality may be activated. It will examine a selection of some studies and provide a summary along with a Consensus Meter illustrating their collective agreement. Try this search: Is white rice linked to diabetes? The Consensus Meter reveals the following outcomes after analyzing 10 papers: 70% indicate a positive association, 20% suggest a possible connection, and 10% indicate no link.

Prompt “ write me a paragraph about the impact of climate change on GDP with citations “

CITATIONS IN CONTEXT

Integrated with Research Solutions.

Over 1.2 billion Citation Statements and metadata from over 181 million papers suggested reference.

How does it work? - "scite uses access to full-text articles and its deep learning model to tell you, for a given publication: - how many times it was cited by others - how it was cited by others by displaying the text where the citation happened from each citing paper - whether each citation offers supporting or contrasting evidence of the cited claims in the publication of interest, or simply mention it."   <https://help.scite.ai/en-us/article/what-is-scite-1widqmr/>

EXAMPLE of seeing all citations and citation statements in one place

More information: Scite: A smart citation index that displays the context of citations and classifies their intent using deep learning  

• GPT3.5 by OpenAI. Knowledge cutoff date is September 2021.
• Input/ Output length - ChatGPT-3.5 allows a maximum token limit of 4096 tokens. According to ChatGPT " On average, a token in English is roughly equivalent to 4 bytes or characters. English words are typically around 5 characters long. This means that, very roughly, you could fit around 800 to 1000 English words within 4096 tokens." 
• According to ChatGPT, the generated responses are non-deterministic by default. So if you run the searches again and get slightly or very different results, it's likely due to this factor.
• ChatGPT may find non-existent references.
• According to this study < https://arxiv.org/ftp/arxiv/papers/2304/2304.06794.pdf > "ChatGPT cites the most-cited articles and journals, relying solely on Google Scholar's citation counts" within the field of environmental science.  
• Example - "INTERVIEW WITH CHATGPT" as a Research Method & Teaching Tool Some researchers began to use this approach to obtain their research data. Try this Google Scholar search link "interview with ChatGPT"   or see two articles below: (1) Chatting about ChatGPT: how may AI and GPT impact academia and libraries? BD Lund, T Wang - Library Hi Tech News, 2023 (2) An interview with ChatGPT: discussing artificial intelligence in teaching, research, and practice , G Scaringi, M Loche - 2023  

Increased risk of sudden infant death syndrome (SIDS) Increased risk of premature birth Increased risk of low birth weight Increased risk of respiratory problems in newborns Increased risk of respiratory problems in infants exposed to secondhand smoke Increased risk of developing asthma and other respiratory illnesses later in life for infants exposed to secondhand smoke [Note : ChatGPT may generate non-existent references or false knowledge. To find out why Large Language Models hallucinate, check out this Wiki article: Hallucination (artificial intelligence) and this blog post -   A Gentle Introduction to Hallucinations in Large Language Models by Adrian Tam ]

Infant death Neonatal mortality (referring specifically to deaths within the first 28 days of life) Perinatal mortality (referring to deaths occurring during the period from 22 completed weeks of gestation to 7 completed days after birth) Early childhood mortality (referring to deaths occurring within the first five years of life) Child mortality (referring to deaths occurring before the age of 18) [Press the Regenerate button to get more.]

• Example -  RELATED WORDS What are the related words of infant mortality? Neonatal mortality, Post-neonatal mortality, Stillbirths, Low birth weight, Malnutrition, Infectious diseases, Vaccination, Maternal health,  Access to healthcare, Poverty, Social inequality, Sanitation, Hygiene, Water quality, Childbirth complications, Congenital abnormalities, Birth defects, Maternal age, Under-five mortality, Child mortality, Perinatal mortality, Preterm birth, Low birth weight, Sudden infant death syndrome (SIDS), Maternal mortality, Postnatal care, Malnutrition, Immunization, Access to healthcare, Clean water and sanitation, Congenital anomalies, Infant health disparities, Infant mortality rate (IMR), Infant survival.  

(("Infant Death"[Mesh] OR "Sudden Infant Death Syndrome"[Mesh] OR "Infant Mortality"[Mesh] OR "Perinatal Mortality"[Mesh] OR "Neonatal Mortality"[Mesh] OR "Fetal Mortality"[Mesh] OR "Infant Death" OR "Sudden Infant Death Syndrome" OR "Infant Mortality" OR "Perinatal Mortality" OR "Neonatal Mortality" OR "Fetal Mortality") AND ("Risk Factors"[Mesh] OR "Etiology"[Mesh] OR "Prevention and Control"[Mesh] OR "Interventions"[Mesh] OR "Public Health"[Mesh] OR "Health Disparities"[Mesh] OR "Healthcare Disparities"[Mesh] OR "Poverty"[Mesh] OR "Malnutrition"[Mesh] OR "Infection"[Mesh] OR "Congenital Abnormalities"[Mesh] OR "Prematurity"[Mesh] OR "Low Birth Weight"[Mesh] OR "Maternal Education"[Mesh] OR "Maternal Health"[Mesh] OR "Risk Factors" OR "Etiology" OR "Prevention and Control" OR "Interventions" OR "Public Health" OR "Health Disparities" OR "Healthcare Disparities" OR "Poverty" OR "Malnutrition" OR "Infection" OR "Congenital Abnormalities" OR "Prematurity" OR "Low Birth Weight" OR "Maternal Education" OR "Maternal Health")) Comments and Suggestions: #1 -This search string may not work on all database platforms. For example, Medline (OVID) may not be able to run it, Medline & CINAHL (EBSCO) can run it without any problems while PubMed will run it but it will indicate which MeSH terms are not indexed. See PubMed's search History and Details under Advanced . #2 - This is just one possible combination. You may need to adjust it based on your task and the databases you are using . #3 - It might be easier if you break the task into 3 parts: ask for synonyms > ask for thesauri terms > and ask it to combine them.

Examples - DATABASE RECOMMENDATIONS Heath Science - Which databases to use to find articles on the EFFECTS OF MATERNAL SMOKING ON INFANT DEATH? PubMed: This is a database of biomedical literature from the National Library of Medicine. It includes articles from medical journals and other sources on a wide range of health-related topics. Embase: This is a database of biomedical literature that covers more international and pharmaceutical content than PubMed. It includes articles from medical journals and other sources on a wide range of health-related topics. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions, including interventions related to maternal smoking and infant death. Scopus: This is a multidisciplinary database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. Web of Science: This is a database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. CINAHL: This is a database of nursing and allied health literature, including articles on maternal smoking and infant death. [Note: The response above was copied and pasted directly from ChatGPT. No editing was added.] Education -- I am doing a meta-analysis on k-12 STEM education. What databases should I use? ERIC : This is a database of education research and information, including articles from journals, reports, and conference papers. It is a commonly used database for educational research. Education Source : This is a comprehensive database of education research and information, including articles from journals, books, and conference papers. Web of Science: This is a multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. Scopus: This is another multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. PsycINFO: This is a database of psychology research, including articles from journals, books, and dissertations. It can be useful for research on STEM education that includes psychological factors. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions including interventions related to education. [Author's note: You could also ask for the GREY LITERATURE sources related to the topic above,]

Example: ACT-AS-AN-EXPERT PROMPT Here's an alternative way to consolidate all the questions into a single consultation by using this popular Act-As-An-Expert prompt, aka, system message prompt:  I am going to conduct a systematic review on games and mathematics related to K-12 education  I want you to act as a systematic review expert . I will ask you some questions related to my research topic and you advise me on how to do it. 

[You may ask one question at a time] My first question is "which databases should I use?"  My second question is "what are the relevant subject terms, descriptors and key words?" My third question is "how to do data extraction?" ..... , .... Please note that the above prompts are merely for illustrative purposes. Actual questions may contain more specific instructions. As an example, for the first question, could you provide guidance on how to identify relevant publications? Specifically, can you provide a list of the primary databases and grey literature sources related to my topic?  

Example - GREY LITERATURE Please show me all the resources that offer grey literature for conducting research in the field of education     ERIC (Education Resources Information Center): https://eric.ed.gov/     OpenGrey: http://www.opengrey.eu/     British Education Index: https://www.ebscohost.com/academic/british-education-index     WorldCat: https://www.worldcat.org/     ProQuest Dissertations & Theses Global: https://www.proquest.com/products-services/pqdtglobal.html     EThOS (Electronic Theses Online Service): https://ethos.bl.uk/     Institutional Repositories of universities and academic institutions (search for specific institution repositories)     American Educational Research Association (AERA): https://www.aera.net/     National Education Association (NEA): https://www.nea.org/     Association for Supervision and Curriculum Development (ASCD): http://www.ascd.org/     RAND Corporation: https://www.rand.org/     National Center for Education Research (NCER): https://ies.ed.gov/ncer/     National Center for Education Statistics (NCES): https://nces.ed.gov/     European Educational Research Association (EERA): https://www.eera-ecer.de/     UNESCO International Institute for Educational Planning (IIEP): http://www.iiep.unesco.org/     Organization for Economic Cooperation and Development (OECD): https://www.oecd.org/education/     Education Development Center (EDC): https://www.edc.org/     National Institute for Educational Policy Research (NIER) - Japan: https://www.nier.go.jp/     Australian Council for Educational Research (ACER): https://www.acer.org/     Canadian Education Association (CEA): https://www.cea-ace.ca/ My topic is about stem education. Which grey literature databases should I use?    STEM Education Research Centre (SERC) Grey Literature Database    National STEM Education Research Repository (NSERR)    National Science Digital Library (NSDL)    STEM Education Resource Center (SERC) GrayLit Network    STEM Education Grey Literature Library

See other Comparison Examples under Bing AI.

Examples - ZERO SHOT, ONE SHOT & FEW SHOT PROMPTING for literature review See the examples on the left panel- How to Fine Tune Prompts

Bing Chat / Copilot

• Bing Chat has become Copilot.
• CONVERSATIONAL LLM 4.0 + SEARCH ENGINE. Connects to the Internet.
• Three conversation modes: More Creative, More Balanced or More Precise.
• Comparison - Prompt: My topic is about psychology. Which grey literature databases should I use? More Precise - PsycExtra, NIH Library and links to library guides, .gov and .org websites More Balanced - PsycExtra and three main research guides that mention psychology grey literature sources. More Creative- PsycExtra, LILACS, and Worldcat + definition of grey literature + suggestions on searching for professional association websites, newsletters, magazines, standards and guidelines, and other sources that may contain relevant information for your topic.
• Some examples below were tested in Bing Chat only.  
• Example - factors of infant mortality Infant mortality is a term that refers to the death of infants before their first birthday. The leading causes of infant mortality include birth asphyxia, pneumonia, congenital malformations, term birth complications such as abnormal presentation of the fetus umbilical cord prolapse, or prolonged labor, neonatal infection, diarrhea, malaria, measles, and malnutrition1. Many situational factors lead to infant mortality such as the pregnant woman’s level of education, environmental conditions, political infrastructure, and level of medical support1. In the United States, a primary determinant of infant mortality risk is infant birth weight with lower birth weights increasing the risk of infant mortality. The determinants of low birth weight include socioeconomic, psychological, behavioral and environmental factors2.  
• Example: PEER REVIEWED SOURCES I need to find some peer reviewed articles about infant mortality? The answer includes 5 articles. The first one is “Causes of death and infant mortality rates among full-term births in the United States between 2010 and 2012: An observational study” by Neha Bairoliya and Günther Fink1. A click on  " Tell me more about the first article " leads to this summary: " The first article is titled “Causes of death and infant mortality rates among full-term births in the United States between 2010 and 2012: An observational study” and was published in PLOS Medicine on March 20, 2018. The authors are Neha Bairoliya and Günther Fink. The study used linked birth and death records for the period 2010–2012 to identify the state- and cause-specific burden of infant mortality among full-term infants (born at 37–42 weeks of gestation) in the United States. The researchers found that the full-term infant mortality rate (FTIMR) was 2.2 per 1,000 live births overall and ranged between 1.29 (Connecticut) and 3.77 (Mississippi) at the state level. Sudden unexpected death in infancy (SUDI) accounted for 43% of FTIM; congenital malformations and perinatal conditions accounted for 31% and 11.3% of FTIM, respectively. The largest mortality differentials between states with good and states with poor FTIMR were found for SUDI, with particularly large risk differentials for deaths due to sudden infant death syndrome (SIDS) and suffocation." More searches: Please find five empirical studies focusing on the factors influencing adult learners engaged in online education. Please locate five scholarly articles on stress management among college students site:pubmed.ncbi.nlm.nih.gov

The ERIC Thesaurus contains nearly 12,000 terms, including more than 4,500 descriptors and 7,000 synonyms1. You can use the term “Academic Achievement” or its synonyms such as “Educational Achievement”, “Student Achievement”, “Academic Performance”, “Academic Success”, “Learning Achievement” and more. [ Note : The follow-up responses include some additional sources. See two below: https://www.powerthesaurus.org/academic_achievement https://eric.ed.gov/?ti=Achievement+Gap   including https://eric.ed.gov/?ti=Academic+Achievement |

My topic is about psychology.  Which grey literature databases should I use?

ChatGPT PsycEXTRA : This database is produced by the American Psychological Association (APA) and includes grey literature such as conference papers, white papers, and government reports. OpenGrey : This database provides access to grey literature produced in Europe, including reports, theses, and conference papers Grey Literature Report : This database is produced by The New York Academy of Medicine and includes reports, conference papers, and other grey literature on health and biomedical topics, including psychology. ProQuest Dissertations and Theses Global : This database provides access to graduate-level research, including theses and dissertations related to psychology. Google Scholar: While not exclusively a grey literature database, Google Scholar can be a useful tool for finding conference papers and other grey literature related to psychology. National Technical Information Service (NTIS) : This database provides access to technical reports produced by U.S. government agencies, including those related to psychology. Bing AI   - [asked in the Precise mode] For psychology, some recommended grey literature databases include PsycEXTRA and PsyArXiv . PsycEXTRA is a database of grey literature material relating to psychology, behavioral sciences and health. PsyArXiv is a psychology archive designed to facilitate rapid dissemination of psychological research. What other models have been developed based on SERVQUAL?

ChatGPT SERVPERF: This is a modified version of SERVQUAL that measures service performance instead of service quality. It was developed by Cronin and Taylor (1992) and is based on the same five dimensions as SERVQUAL. SERVPERF-GAP: This model, developed by Caruana and Ewing (2006), extends the SERVQUAL model to include three additional gaps that can occur when customers evaluate service quality. E-SERVQUAL: This model, developed by Parasuraman et al. (2005), adapts the SERVQUAL scale to measure the quality of online services. SERVCO: This is a modified version of SERVQUAL that includes a sixth dimension, "cost," in addition to the five original dimensions. It was developed by Sureshchandar et al. (2002) to address the importance of cost in service quality evaluation. SERVQ-HC: This is a modified version of SERVQUAL that is specifically designed for evaluating the quality of health care services. It was developed by Cronin et al. (2000) and includes 20 items across five dimensions. Bing AI The Nordic model of service quality2. The hierarchical model of service quality3. The American Customer Satisfaction Index (ACSI)4.

     Bing AI Sidebar - CHAT, THINK, & WRITE

• Examples of Using AI sidebar to Recap Google Scholar findings

Chat - If you highlight a study in the search results of Google Scholar, you will be prompted with a question by AI sidebar asking if you want to send the selected text to it. If you choose to do so, you can then select either  EXPLAIN or EXPAND to learn more about the chosen article. It's worth noting that EXPAND provides more detailed information. You can then click on any of the follow-up links to delve further into the selected article or topic. If the text of the chosen study is written in a foreign language, the AI sidebar can also provide an explanation of the text in English. Another option for extracting the key points from a selected article is to submit the URL of the PDF. Insights - Use the insights button to get more ideas about the topic. Compose - Tell the Edge sidebar your topic and let its Compose tool to generate a draft for you. Google Scholar Button- See also the Plugins and Extension page for how to perform a combined search using Google, Google Scholar, and ChatGPT .

Example: FINDING SIMILAR ARTICLES Find similar articles like this one - [then paste in the abstract ] Note - Use this prompt with Bing chat since real-time web info is required.

Examples: SUMMARIZE + REFERENCE Use a basic prompt like " Please summarize . ..." or add a REFERENCE TEXT that provides the necessary information about what you want it to focus or how the summary or resolution should look like. The reference could be a quote, an excerpt, a partial sentence, a conversation, an abstract, a code snippet and so on. Formula : Specify a role > assign a task > provide a reference text. Example#1 - Scholarly Journal Quote

STEP 1 Prompt: As a research assistant specializing in renewable energy, your task is to locate comparable research studies based on the provided abstract from an article: "This paper discusses the perspective of renewable energy (wind, solar, wave and biomass) in the making of strategies for a sustainable development. Such strategies typically involve three major technological changes: energy savings on the demand side, efficiency improvements in the energy production, and replacement of fossil fuels by various sources of renewable energy."

Bing Chat then found 3 documents: the ScienceDirect paper where the abstract came from and two other documents from un.org and frontiersin.org respectively.

STEP 2 Prompt: Please synthesize the findings of the three studies provided above.

Bing Chat: "Sure! Here is a synthesis of the findings from the three studies:

All three studies emphasize the importance of renewable energy in achieving sustainable development and mitigating climate change. They all discuss various strategies and actions that can be taken to increase the use of renewable energy sources and reduce reliance on fossil fuels.

Henrik Lund’s paper discusses the perspective of renewable energy (wind, solar, wave and biomass) in the making of strategies for a sustainable development. Such strategies typically involve three major technological changes: energy savings on the demand side, efficiency improvements in the energy production, and .....

The United Nations outlines five critical actions the world needs to prioritize now to transform our energy systems and speed up the shift to renewable energy: Make renewable energy technology a global public good, Improve global access to components and raw materials......

“Sustainable Energy Transition for Renewable and Low Carbon Grid” discusses that a sustainable global electricity transition will entail increased use of renewable energy sources particularly wind and solar, nuclear energy as a low carbon energy source, electrification of transport and.......

In summary , these studies suggest that transitioning to renewable energy sources is crucial for sustainable development and mitigating climate change. This can be achieved through various strategies such as increasing energy efficiency, improving access to renewable technology and materials, leveling the playing field for renewables, ending fossil fuel subsidies, and redirecting investments towards renewables." Example #2 Y ou are an expert researcher, given the following article, please discuss its key findings. Reference: How Large Language Models are Transforming Machine-Paraphrased Plagiarism at https://arxiv.org/abs/2210.03568 This is another way to put REFERENCE TEXT. As a side not, role specifying or the use of persona is important as it can impact the level of responses obtained. Just imagine if the designated role were " You are a high school student... ." Example #3 Please read this article and summarize it f or me - "Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making" and then find 5 similar studies and please also summarize each for me.

CONNECTED PAPERS

• RELATED STUDIES
• Uses visual graphs or other ways to show relevant studies. The database is connected to the Semantic Scholar Paper Corpus which has compiled hundreds of millions of published papers across many science and social science fields.
• See more details about how it works .  
• Example - SERVQUAL and then click on SELECT A PAPER TO BUILD THE GRAPH > The first paper was selected. Results: (1) Origin paper - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality + Connected papers with links to Connected Papers / PDF / DOI or Publisher's site / Semantic Scholar / Google Scholar. (2) Graph showing the origin paper + connected papers with links to the major sources . See above. (3) Links to Prior Works and Derivative Works See the detailed citations by Semantic Scholar on the origin SERVQUAL paper on the top of this page within Semantic Scholars.
• How to Search Search by work title. Enter some keywords about a topic.
• Download / Save Download your saved Items in Bib format.

PAPER DIGEST

• SUMMARY & SYNTHESIS
• " Knowledge graph & natural language processing platform tailored for technology domain . <"https://www.paperdigest.org/> Areas covered: technology, biology/health, all sciences areas, business, humanities/ social sciences, patents and grants ...

• LITERATURE REVIEW - https://www.paperdigest.org/review/ Systematic Review - https://www.paperdigest.org/literature-review/
• SEARCH CONSOLE - https://www.paperdigest.org/search/ Conference Digest - NIPS conference papers ... Tech AI Tools: Literature Review  | Literature Search | Question Answering | Text Summarization Expert AI Tools: Org AI | Expert search | Executive Search, Reviewer Search, Patent Lawyer Search...

Daily paper digest / Conference papers digest / Best paper digest / Topic tracking. In Account enter the subject areas interested. Daily Digest will upload studies based on your interests.

RESEARCH RABBIT

• CITATION-BASED MAPPING: SIMILAR / EARLY / LATER WORKS
• " 100s of millions of academic articles and covers more than 90%+ of materials that can be found in major databases used by academic institutions (such as Scopus, Web of Science, and others) ." See its FAQs page. Search algorithms were borrowed from NIH and Semantic Scholar.

The default “Untitled Collection” will collect your search histories, based on which Research Rabbit will send you recommendations for three types of related results: Similar Works / Earlier Works / Later Works, viewable in graph such as Network, Timeline, First Authors etc.

Zotero integration: importing and exporting between these two apps.

• Example - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality [Login required] Try it to see its Similar Works, Earlier Works and Later Works or other documents.
• Export Results - Findings can be exported in BibTxt, RIS or CSV format.

CITING GENERATIVE AI

• How to cite ChatGPT  [APA] - https://apastyle. apa.org/blog /how-to-cite-chatgpt  
• How to Cite Generative AI  [MLA]  https://style. mla.org /citing-generative-ai/
• Citation Guide - Citing ChatGPT and Other Generative AI (University of Queensland, Australia)
• Next: Dialogues: Insightful Facts >>
• Last Updated: May 9, 2024 2:16 PM
• URL: https://tamu.libguides.com/c.php?g=1289555

AI for literature reviews

Let ai assist boost your literature review and analysis, how to use ai assist for your literature review.

• Step one: Identify and import your literature
• Step two: Summarize your documents with AI Assist
• Step three: Determine relevance and sort accordingly
• Step four: Reading and rough coding
• Step five: Confirm your initial codings
• Step six: Refine your code system
• Step seven: Analyze your literature

Literature about literature reviews and analysis

Tuesday, September 19, 2023

As you may have noticed, there is a rapid growth in AI-based tools for all types of software packages. We followed this trend by releasing AI Assist – your virtual research assistant that simplifies your qualitative data analysis. In the following, we will present you the tools and functions of AI Assist and how they can facilitate your literature reviews.

Literature reviews are an important step in the data analysis journey of many research projects, but often it is a time-consuming and arduous affair. Whether you are reviewing literature for writing a meta-analysis or for the background section of your thesis, work with MAXQDA! Besides the classic tools of MAXQDA that can facilitate each phase of your literature review, the new tool AI Assist can boost your literature review and analysis in multiple ways.

Year by year, the number of publications grows in almost every field of research – our insights and knowledge likewise. The drawback is that the number of publications might be too high to keep track of the recent developments in your field of research. Consequently, conducting a proper literature review becomes more and more difficult, and the importance of quickly identifying whether a publication is interesting for your research question constantly increases.

Luckily, MAXQDA’s AI Assist tool is here to help. Among others, it can summarize your documents, text segments, and coded segments. But there is more – based on your coded segments AI Assist can generate subcodes suggestions. In the following, we will present you step-by-step instructions on how to use MAXQDA for your literature review and analysis with a special focus on how AI Assist can support you.

Step one of AI for literature reviews: Identify and import your literature

Despite the fact that MAXQDA and AI Assist can facilitate your literature review and analysis in manifold ways, the best advice is to carefully plan your literature review and analysis. Think about the purpose of your literature review and the questions you want to answer. Develop a search strategy which includes, but is not limited to, deciding on literature databases, search terms, and practical and methodological criteria for selecting high-quality scientific literature. Then start your literature review and analysis by searching the identified databases. Before downloading the PDFs and/or bibliographic information (RIS), briefly scan the search results for relevance by reading the title, keywords and abstract. If you find the publication interesting, download the PDF, and let AI Assist help you determining whether the publication falls within the narrower area of your research question.

MAXQDA’s import tab offers import options dedicated to different data types, such as bibliographic data (in RIS file format) and PDF documents. To import the selected literature, just click on the corresponding button, select the data you want to import, and click okay. Alternatively, you can import data simply by drag-and-dropping the data files from your Windows Explorer/Mac Finder window. If you import full texts and the corresponding bibliographic data, MAXQDA automatically connects the full text to the literature entry with an internal link.

Step two of AI for literature reviews: Summarize your documents with AI Assist

Now that you have imported all publications that might be interesting for your research question, it is time to explore whether they are indeed relevant for your literature review and analysis. Before the release of AI Assist, this step typically took a lot of time as you had to go through each paper individually. With the release of AI Assist, MAXQDA can accelerate this step with AI-generated summaries of your publications. For example, you can create AI-generated summaries either for the entire publication or for each chapter (e.g. Introduction, Methods, Results, and so on) individually and base your decision about a paper’s relevance on these summaries. Each AI-generated summary is stored in a memo that is attached to the underlying document or text segment, respectively.

Summarizing text segments with AI Assist just takes a few clicks. Simply highlight a text segment in the Document Browser and choose AI Assist from the context menu. Adjust the settings to your needs and let OpenAI do the work for you. To view and edit the summary, double-click on the yellow memo icon attached to the summarized text passage.

Adjust settings for summarizing text with AI Assist for literature reviews

Step three of AI for literature reviews: Determine relevance and sort accordingly

Instead of reading the entire paper, you can use the AI-generated summaries to determine whether a publication falls within the narrower area of your research question. To do so, it might be helpful to view all memos containing summaries of a specific publication at once. Of course, this is possible with MAXQDA. Go to the Memo tab, click on (In-)document Memos, and click on the publication’s name to view only the AI-generated summaries related to this document. It is important to note that AI-generated summaries are not perfect yet. Therefore, it is advisable to read the entire paper in cases where you have doubts or can’t decide whether the publication is relevant.

Depending on the number of publications in your MAXQDA project, you might want to sort your documents in document groups, for example, based on the relevance for your research question or the topics discussed in the paper. You can easily create a new Document group by clicking on the respective icon in the Document System window. Documents can be added simply via drag-and-drop. Alternatively, you can create Document Sets which are especially helpful when you want to sort your documents by more than one domain (e.g. by relevance and methodology used).

Sort documents in document groups according to their relevance using AI for literature reviews

Step four of AI for literature reviews: Reading and rough coding

Now that you have identified the publications important to your project, it is time to go through the documents. Although, AI Assist can support you at multiple stages of your literature review, it can’t replace the researcher. As a researcher, you still need a deep understanding of your material, analysis methods, and the software you use for analysis. As AI-generated summaries are not perfect yet, you might want to improve the summaries, if necessary, or add information that you consider especially important, e.g. participants’ demographics.

In a next step, it is time to create and apply some codes to the data. A code can be described as a label used to name phenomena in a text or an image. Depending on your approach, you might already have codes in mind (deductive coding) or you plan to generate codes on the basis of the data (inductive coding). No matter your approach – you can use MAXQDA’s advanced tools for coding. In many cases it is best, to start your first round of coding with rather rough codes that you can refine in a later step using the help of AI Assist. You can create codes in the Code System window by clicking on the plus-icon or in the Document Browser by highlighting a text segment via the context menu or the corresponding icons. A code can be applied to the data via drag-and-drop.

Reading and rough coding for AI for literature reviews

Step five of AI for literature reviews: Confirm your initial codings

Though AI Assist can’t validate your codings like a second researcher using intercoder agreement, AI Assist’s Code Summaries can help you to identify whether you have applied the code as intended. The AI-generated Code Summary is a summary of the content of all text segments coded with the corresponing code. This summary might give you an idea of how you have applied the code and if the coded text segments indeed contain what you had in mind when creating the code.

To create a summary of coded segments with AI Assist, simply right-click the code of interest in the Code System and choose AI Assist > Code Summary from the context menu. Adjust language and the summary length to your needs and let AI Assist do the summary for you. As for document summaries, the summary will be stored in a memo which is placed next to the code in the Code System. If the summary doesn’t match your code definition, you might want to review the coded segments and adjust your codings accordingly. By double-clicking on a code, you open the Overview of Coded Segments – a table perfectly suited to go through the coded segments and adjust or remove the codings.

Confirm your initial codings with AI Assist’s Code Summary for literature reviews

Step six of AI for literature reviews: Refine your code system

In case you have applied rather rough codes to your data, your code definitions are probably too broad for you to make sense of the data. Depending on your goals, you might wish to refine these rather broad codes into more precise sub-codes. Again, you can use AI Assist’s power to support this step of your literature review. AI Assist analyzes the text and suggests subcodes while leaving the decision on whether you want to create the suggested sub-codes up to you.

To create AI-generated subcode suggestions, open the context menu of a code and choose AI Assist > Suggest Subcodes. Besides selecting a language, you can ask AI Assist to include examples for each subcode as a bullet list. Like the AI-generated summaries, the code suggestions are stored in the code’s memo. If you are satisfied with the code suggestions, you can create and apply them to your data. Alternatively, you can use the AI-generated code suggestions to confirm the subcodes that you have created.

Use AI Assist’s Suggest Subcodes function to refine your code system for your literature reviews

Step seven of AI for literature reviews: Analyze your literature

Now that you have coded your literature, it’s time to analyze the material with MAXQDA. Although you can use plenty of MAXQDA’s tools and functions even when the material is not coded, other tools require coded segments to be applicable. MAXQDA offers plenty of tools for qualitative data analysis, impossible to mention all. Among others, MAXQDA’s Overview and Summary Tables are useful for aggregating your data. With MAXQDA Visualization Tools you can quickly and easily create stunning visualizations of your data, and with MAXQDA’s Questions-Themes-Theories tool you have a place to synthesize your results and write up a literature review or report.

You can find more information and ideas for conducting a literature review with MAXQDA, here:

Learn more about literature reviews

For information about AI Assist and how to Activate AI Assist, visit:

Learn more about AI Assist

We offer a variety of free learning materials to help you get started with your literature review. Check out our Getting Started Guide to get a quick overview of MAXQDA and step-by-step instructions on setting up your software and creating your first project with your brand new QDA software. In addition, the free Literature Reviews Guide explains how to conduct a literature review with MAXQDA in more detail.

Getting Started with MAXQDA

Literature Reviews with MAXQDA

MAXQDA Newsletter

Our research and analysis tips, straight to your inbox.

• By submitting the form I accept the Privacy Policy.

RAxter is now Enago Read! Enjoy the same licensing and pricing with enhanced capabilities. No action required for existing customers.

Your all in one AI-powered Reading Assistant

A Reading Space to Ideate, Create Knowledge, and Collaborate on Your Research

• Smartly organize your research
• Receive recommendations that cannot be ignored
• Collaborate with your team to read, discuss, and share knowledge

From Surface-Level Exploration to Critical Reading - All in one Place!

Fine-tune your literature search.

Our AI-powered reading assistant saves time spent on the exploration of relevant resources and allows you to focus more on reading.

Select phrases or specific sections and explore more research papers related to the core aspects of your selections. Pin the useful ones for future references.

Our platform brings you the latest research related to your and project work.

Speed up your literature review

Quickly generate a summary of key sections of any paper with our summarizer.

Make informed decisions about which papers are relevant, and where to invest your time in further reading.

Get key insights from the paper, quickly comprehend the paper’s unique approach, and recall the key points.

Bring order to your research projects

Organize your reading lists into different projects and maintain the context of your research.

Quickly sort items into collections and tag or filter them according to keywords and color codes.

Experience the power of sharing by finding all the shared literature at one place.

Decode papers effortlessly for faster comprehension

Highlight what is important so that you can retrieve it faster next time.

Select any text in the paper and ask Copilot to explain it to help you get a deeper understanding.

Ask questions and follow-ups from AI-powered Copilot.

Collaborate to read with your team, professors, or students

Share and discuss literature and drafts with your study group, colleagues, experts, and advisors. Recommend valuable resources and help each other for better understanding.

Work in shared projects efficiently and improve visibility within your study group or lab members.

Keep track of your team's progress by being constantly connected and engaging in active knowledge transfer by requesting full access to relevant papers and drafts.

Find papers from across the world's largest repositories

Testimonials

Privacy and security of your research data are integral to our mission..

Everything you add or create on Enago Read is private by default. It is visible if and when you share it with other users.

You can put Creative Commons license on original drafts to protect your IP. For shared files, Enago Read always maintains a copy in case of deletion by collaborators or revoked access.

We use state-of-the-art security protocols and algorithms including MD5 Encryption, SSL, and HTTPS to secure your data.

Using scite for literature reviews and critical analysis

Using scite to speed up literature reviews and critical analysis 🚀, finding relevant works, scite search: sorting, citation filters and aggregations.

Collecting works in a dashboard and staying up to date on new citations and publications

Citation chaining, forward chaining.

Backward chaining

Side chaining (finding co-citations)

Critically Engaging with a publication and its results

Using results, arguments, methodologies presented citation statements to perform a critical analysis.

Citation statement search

Adding nuance to your citations

Identifying gaps in the literature, understanding the current state of the art.

Finding differences in results

Finding suggested areas of investigation

Updated on: 09/03/2021

Was this article helpful?

Share your feedback

• FIU Libraries
• RefTech LibGuides
• Artificial Intelligence Now: ChatGPT + AI Literacy Toolbox
• Literature Reviews with Prompts

Artificial Intelligence Now: ChatGPT + AI Literacy Toolbox: Literature Reviews with Prompts

• Literacy Tutorials
• AI LibGuides
• AI Literacy
• AI + Art News
• AI Plagiarism + Citation
• Which AI tools should I choose?
• Faculty + Academic Writing
• ChatGPT on InfoLit
• Libraries + AI
• Art + Image Prompts
• Prompt Literacy
• Text Prompts
• Scholarship + Publishing
• Students + AI Use
• FIU Library Resources
• How does ChatGPT work?
• Zoom Recordings: AI Workshops
• ALA 2024: Breaking Boundaries

Resources on Lit Reviews & AI

• How to Use ChatGPT to Accelerate Literature Review I’d like to show you how I use ChatGPT to speed up my literature review process. The topic I am exploring is heterogeneity(diversity) learning. I started with the keyword “Info-GAIL” as I read about it when using GAIL in the past.
• ChatGPT Simple Literature Review Template The evolution of library services in the digital age has seen a significant shift towards automation and artificial intelligence applications, with OpenAI's ChatGPT being one of the most popular tools. This literature review explores the trends in the application of ChatGPT in library settings, focusing on user engagement and support services from 2015 to 2023.
• ChatGPT as a Tool for Library Research – Some Notes and Suggestions I see ChatGPT and its alternatives as having partial value as tools for library searching. You can use them without any training, but they will perform better when you know some details about them.

9 Ways To Use ChatGPT To Write A Literature Review (WITHOUT Plagiarism) Video

• Step-by-Step

How to Use ChatGPT to Write a Literature Review With Prompts

Dr. Somasundaram R | https://www.ilovephd.com/ | Copyright © 2019-2023 – iLovePhD | May 19, 2023

Writing a literature review can be a challenging task for researchers and students alike. It requires a comprehensive understanding of the existing body of research on a particular topic. However, with the advent of advanced language models like ChatGPT, the process has become more accessible and efficient.

Discover how to effectively utilize ChatGPT as a research assistant to write a comprehensive and SEO-friendly literature review. Follow our step-by-step guide to leverage this powerful tool, optimize your review for search engines, and contribute to the scholarly conversation in your field.

A Step-by-Step Guide: How to Use ChatGPT for Writing a Literature Review

Step 1: Defining Your Research Objective Before diving into the literature review process, it is crucial to define your research objective.

Clearly articulate the topic, research question, or hypothesis you aim to address through your literature review. This step will help you maintain focus and guide your search for relevant sources.

Step 2: Identifying Keywords and Search Terms To effectively use ChatGPT to assist in your literature review, you need to identify relevant keywords and search terms related to your research topic.

These keywords will help you narrow down your search and gather pertinent information. Consider using tools like Google Keyword Planner or other keyword research tools to discover commonly used terms in your field.

Step 3: Familiarizing Yourself with ChatGPT Before engaging with ChatGPT, it is essential to understand its capabilities and limitations. Familiarize yourself with the prompts and commands that work best with the model.

Keep in mind that ChatGPT is an AI language model trained on a vast amount of data, so it can provide valuable insights and suggestions, but it’s important to critically evaluate and validate the information it generates.

Step 4: Generating an Initial Literature Review Outline Start by creating an outline for your literature review. Outline the main sections, such as the introduction, methodology, results, discussion, and conclusion.

Within each section, jot down the key points or subtopics you want to cover. This will help you organize your thoughts and structure your review effectively.

Step 5: Engaging with ChatGPT for Research Assistance Once you have your outline ready, engage with ChatGPT for research assistance.

Begin by providing a clear and concise prompt that specifies the topic, context, and any specific questions you have. For example, “What are the current trends in [your research topic]?” or “Can you provide an overview of the main theories on [your research question]?”

Step 6: Reviewing and Selecting Generated Content ChatGPT will generate a response based on your prompt. Carefully review the content generated, considering its relevance, accuracy, and coherence.

Extract key points, relevant references, and insightful arguments from the response and incorporate them into your literature review. Be sure to cite and attribute the sources appropriately.

Step 7: Ensuring Coherence and Flow While ChatGPT can provide valuable content, it’s important to ensure the coherence and flow of your literature review.

Use your critical thinking skills to connect the generated content with your research objective and existing knowledge. Rearrange, rephrase, and expand upon the generated text to ensure it aligns with the structure and purpose of your review.

Step 8: Editing and Proofreading Once you have incorporated the generated content into your literature review, thoroughly edit and proofread the document.

Check for grammatical errors, consistency in referencing, and overall clarity. This step is crucial to ensure your literature review is polished and professional.

ChatGPT prompts to Write a Literature Review

Prompts you can use when engaging with ChatGPT for research assistance in writing a literature review:

“Can you provide an overview of the main theories and concepts related to [your research topic]?”

“What are the current trends and developments in [your research field]?”

“Can you suggest some key studies or research papers on [specific aspect of your research topic]?”

“What are the main methodologies used in conducting research on [your research topic]?”

“Can you provide a critical analysis of the existing literature on [your research question]?”

“Are there any gaps or areas of controversy in the literature on [your research topic] that need further exploration?”

“What are the key findings and conclusions from the most recent studies on [your research topic]?”

“Can you suggest some reputable journals or publications explore for relevant literature in [your research field]?”

“What are the different perspectives or schools of thought in the literature on [your research topic]?”

“Can you provide a summary of the historical background and evolution of research on [your research topic]?”

Remember to provide clear and specific instructions in your prompts to guide ChatGPT in generating relevant and accurate content for your literature review.

Using ChatGPT to write a literature review can greatly facilitate the research process. By following a step-by-step approach, researchers can effectively leverage ChatGPT’s capabilities to gather insights, generate content, and enhance the quality of their literature review. However, it is important to approach the generated content critically, validate it with reliable sources, and ensure coherence within the review.

• << Previous: Art + Image Prompts
• Next: Prompt Literacy >>
• Last Updated: May 17, 2024 11:00 AM
• URL: https://library.fiu.edu/ai

• Upcoming Webinar
• Upcoming Webinar: AI & Lit Review
• Effortless AI
• Effortless Note Taking
• Effortless Literature Review
• Effortless Knowledge Management
• Free 8-day note-taking course

Review: Consensus AI – An Intelligent Literature Review Companion

• by Ilya Shabanov
• May 18, 2024 May 18, 2024
• AI , literature review , tool-review

The way we extract information for literature reviews has completely changed in the age of AI. While reading and understanding are still essential, finding the correct information quickly becomes accelerated with tools like Consensus. At it’s core Consensus is a search engine with AI built within and around it to speed up your research. It scans millions of papers to find the ones that match your query and sort them by which support or reject your argument or employ specific methods. This makes searching for the right paper faster, more enjoyable, and effortless.

Join the Effortless Newsletter. Receive free tips on note-taking, literature review, AI tools, and other productivity topics specifically tailored for academics and students.

In this review, we will break down the main use cases, limitations, and features of consensus in detail. First, we will look at what Consensus is and what it does, then dive deep into every feature and finish with an even more innovative use case: ConsensusGPT, which combines ChatGPT’s conversational capabilities with Consensus’ expansive database.

• What problem does Consensus solve?
• What does Consensus AI do?
• The Consensus meter for a quick overview
• Synthesize and CoPilot boxes to grasp a topic
• Badges/Summaries to sort single studies
• Filtering options in Consensus

ConsensusGPT: Consensus as a ChatGPT plugin

What is the difference between chatgpt and consensus.

• Academic writing use-case: Asking Consensus for evidence
• Academic writing use-case: Filling in Citations

How to use Consensus AI?

Like all AI tools, Consensus is as simple as typing a question into the textbox. You can start using it for free, and if you need it, get the premium membership, which allows you to use AI to summarize findings and systematically analyze single papers (more than one pricing in the last section of this post and a 30% off discount code! ). However, it is crucial to understand this technology’s limitations and know which results you can fully trust and which you need to double-check.

To use Consensus you will require a free account. The results have four main elements: Summary, Consensus Meter, Copilot, and about ten papers. If you are not a premium member, you will always see the papers, but the other elements are limited to a certain amount of monthly searches.

Compare the result in the screenshot above with the Google search for yourself (“Does climate change cause range shifts in forests?” ). Despite being a big and somewhat generalizing question, I got a concise reply. The devil is, of course, in the detail with every scientific question, but you see that finding tentative answers to complex questions becomes increasingly simple. If I am brainstorming parts of my research, I might ask dozens of questions like this, and understanding what works in seconds rather than hours makes the research process smooth.

At the end of your search you will find a number of studies sorted by relevance clicking on each of those brings the detailed study view:

This view brings together all the different pieces of Information has on this study which includes metadata, summaries, quality indicators, citation counts and a link to the publication itself.

Can you trust what Consensus AI tells you?

This is a general debate about how much we should trust AI. In my opinion, it is not different from asking a human. If you ask a five-year-old kid a serious question, you will certainly not bet on the correctness. If the kid is 16 and their answer is surprising but not unrealistic, you might trust but double-check. If a professor with 40 years of experience answers a question in their domain, your answer is as firm as it gets. The problem with AI is we don’t know which personas we are talking to.

My rule of thumb is to consider how much data has been published on a topic. If I am asking a question that has been debated for decades, there is likely a large amount of data available, and I tend to trust AI (like in the example question above). The more recent and specialized topic you are interested in, the less you should trust any AI on this. Luckily, Consensus spots these cases sometimes:

Overall, the speed of AI is increasing very fast, and the training datasets are growing daily. Don’t hesitate to be specific and treat Consensus as a new colleague you know is knowledgeable but has yet to talk to them much. Get to know one another.

Questions Consensus AI works best with

To get the most out of Consensus ask supported questions: ✅ Yes / No ✅ Relationship (e.g. Is Sauna beneficial for blood pressure) ✅ Benefits of… (e.g. “Sauna”) Open-ended questions or ones that require numbers/explanations MAY or MAY NOT work. This is a general case with AI. Questions requiring logical reasoning and thinking rarely produce excellent results (at least as of early 2024). Bad example: “How much climate change can European forests tolerate?”. While you will almost always get a reply from the AI, the value will diminish the more you deviate from questions AI can answer. This is not a particular limitation of consensus, but it will generally apply to large language models since they deal with facts as language rather than logically connected entities.

You can check out the much more detailed guide on the Consensus FAQ page . The best way to find out, however is to just try it out for yourself.

Domains Consensus AI works best with

According to the Consensus website, the best questions are in the medical and social policy domain. I have been using it for my research (forest ecology), and it has always come up with good studies and answers despite needing to be added to this list. It is best to try out the domain you already know and see if the search finds the essential papers you know are central to it.

However, the interface is designed with medical studies in mind. For example, you can filter by human/animal studies or find randomized control trials, concepts that don’t exist in ecology. However, the UI will likely change in the future as Consensus gets more adopted and expanded across all domains.

Limitations of Consensus AI

The two most significant limitations of all AI tools are incompleteness and irreproducibility . Incompleteness means that the results you get are filtered by an AI model with a certain level of randomness. We don’t truly understand how this process works, so it might sometimes miss something that a human would deem necessary. This is especially true since we need to know which papers Consensus can access.

This brings us to the second issue: Irreproducibility, which is of particular concern when conducting a systematic literature review. Such a review involves documenting your paper search process, theoretically allowing for replication. However, if you were to state, for instance, ‘I searched for X on Consensus’, and someone attempted to replicate this a year later, their findings might differ from yours. This variation directly results from the stochastic nature inherent in all AI models.

Remember, searching for an AI is like asking somebody for directions to a restaurant. You will generally provide the same reply to different people, but you will never use the exact words and add/omit specific, more minor details.

The Consensus Meter for yes/no Questions

The Consensus Meter consists of three bars: Yes, No, and Possibly. The way it works is that the Consensus AI first finds several papers related to your query, scans them, and then sorts them into one of the three categories. If most papers affirm your question, the yes bar will grow. This is why Consensus invites you to use yes/no questions. Otherwise, the meter would make little sense. To use this feature, you need to enable the “Synthesize” checkbox right below the search bar. You get 20 of those summaries for free monthly and must purchase a premium account if you need more.

This feature is handy even when researching what supplements to take or what exercise to prioritize daily. In my experience, I tend to trust this reply over clickbait Google articles written primarily for SEO (Search Engine Optimisation) and “approved” by somebody with a doctoral degree, as their purpose is mainly to rank high in the Google search and only secondary to providing scientifically correct output.

Synthesize and CoPilot for Topical Overview

The synthesize (or summary), and Copilot features are more in-depth AI features that process the search results (i.e., the top 10 papers answering your question) and summarize them. The summary feature creates a very short summary (~50 words), while Copilot creates a lengthy text of about 400 words with references to the search results below.

To use these features, activate the “Synthesize” and “Copilot” checkboxes right below the search bar in Consensus. Be aware that they both cost “AI credits.” 20 AI credits are free every month. Synthesize costs one credit per query, and Copilot costs two. If you are in a free account, I suggest you save these questions for the relevant questions and use them selectively and judiciously.

The Copilot is 100% free of hallucinations as it can only use the papers retrieved from the database.

Customizing Copilot with queries

While Syntehesize is fixed feature, Copilot can be customized to your needs by adding instructions to it. Think of it as an upgraded ChatGPT version that has access to the contents of all the papers that Consensus found for your query. Essentially this allows you to write a mini literature review. Here, I ask to generate a bullet-point list of the main drivers of forest range shifts. And Copilot solves the task for me:

When we keep the question but change the prompt the result changes. For example, here I ask to draft an outline of a literature review. Notice how useful this can be when starting out with a topic and seeking general guidance on how to solve a problem:

However, Consensus is primarily a search engine not a conversational AI. If you are learning a topic and want to have a back and forth conversation use the Consensus GPT bot (section below) instead.

Badges and Study Snapshops to Identify Relevant Studies

Badges and snapshots allow users to investigate a single study of interest. This is where Consensus’s strengths for medical-type questions shine, as the snapshots and badges lean towards medical studies and feature options like “animal trials” or “randomized controlled trials.” To generate a study snapshot, click on “Study Snapshot” right below the paper.

In the medical example above, you immediately see who the test subjects were, how many, which methods were used, and many other details that would likely take a while to find in the paper’s methods section.

Badges follow a similar idea but highlight different important properties of studies. For example, some studies might have more citations, while others employ a particular method. Badges make it easier to find papers that stand out.

There are many different badges and when you hover them with the mouse a small popup explains what they mean.

Filtering Options in Consensus

Since Consensus is primarily a search engine, you can filter your results like on PubMed. However, there is a big difference because Consensus filters the results using semantic search and AI, which allows filtering by content rather than words in the title/abstract.

Especially for medical questions where sample size or human studies are essential distinguishing factors, this search is unique. I hope that one day, Consensus will implement similar filters to search in my domain (ecology), for example, by study location, taxa, or statistical methods.

Not too long ago, ChatGPT released so-called GPTs or customized AI assistants that use ChatGPT but add the ability to communicate with other services (like Consensus). The result is an entire ecosystem of assistants for hundreds of use-cases. Here are my top 5 GPTs for academic purposes . Consensus has been featured in the GPT store from the first day and remains among the top GPTs, which is a testimony to its usefulness.

To use ConsensusGPT you will need a premium subscription to ChatGPT. Should you get one? I wrote a thread with my thoughts on this .

While you will find the same papers using ConsensusGPT or a website, you will generally have a different approach to using them. A GPT is just ChatGPT with a few extra instructions and the ability to call other services like consensus to ask, for example, for papers. So, while Consensus provides the data and some instructions, ChatGPT generates the text.

This allows for significant use cases like finding evidence for questions and having long conversations where you alternate between accessing knowledge from ChatGPT and querying papers from consensus. If you are curious, check out the Effortless Literature Review 3 webinar , where I heavily relied on this technique.

The downside is that you do not have access to the Consensus meter or the content of the papers like Consensus does on the website. Overall, this means that you can do a broader literature review that is slightly shallower. However, Consensus GPT provides a link to their website where you can continue to use the features introduced above.

If you want to start building a team of AI helpers for your academic career, check out my tutorial on building GPTs or dive as deep as possible by taking the Effortless AI course .

Is ConsensusGPT free?

Yes it is if you have a ChatGPT Premium subscription. It delivers more or less the same functionality when searching on the Consensus website (which is free there, too). However, to get insights from inside the single papers, you will need to use the Consensus website and their AI to analyse the results in-depth.

Academic writing use-case: Asking Consensus for Evidence

Below is a use case I often use when writing a paper. Usually, I know certain things are true because I have read them many times but don’t have a specific citation in mind to back them up in a published paper. This is where you can use ConsensusGPT. Use the straightforward prompt “Find evidence for …”. You can use The results of several studies as a reference in your writing.

It goes without saying that you should always double check the reply by at least skimming the paper. Keep in mind that often AIs will not have access to the entire PDF but only the publicly available abstract and its conclusions might therefore be incomplete.

Consensus AI vs SciSpace

Both companies have similar capabilities and the same goal. While SciSpace shines at using AI to help you read papers and discover related papers, Consensus extracts essential information from a collection of documents. It displays the final results as a quick, easily digestible summary. Consensus shines regarding Yes/No questions in the medical domain as its UI is optimized towards this, as evidenced by various filter options, the consensus meter, and badges. If you want to learn more about SciSpace, read my deep dive on SciSpace .

Consensus AI Pricing

Consensus works on a so-called freemium model. Some free features, including search results (papers) and badges, are forever free. This lets you know which papers are relevant but uses something other than AI to extract the appropriate insights. For this, you need the premium plan. However, Consensus allows you to try out the advanced features: Summary and Copilot up to 20 times a month. For this so-called AI, credits are consumed, of which you have 20 free every month. You use one of those credits (two for Copilot) whenever you create a summary.

Feel free to use the discount code Effortless30 for a 30% discount (I don’t even get any commission from it, by the way). Students can purchase the premium account at a 40% discount and the general price is 9$ per month.

Overall Consensus is a novel way to discover literature that particularly shines when you ask it medical yes/no questions as its UI has been designed with these papers in mind. It is equally useful in an academic context as well as just for you personally to answer some health related question.

• It starts with a plain text query and delivers a set of papers that help answer this query.
• If you ask it a yes/no question, Consensus will analyze how each paper leans and display that as a small yes/no/possibly graph called the Consensus Meter
• If you are a premium member, AI will analyze the resulting papers and create an outline with citations in an academic fashion.
• Consensus is available as GPT in ChatGPT, which allows for unique use cases as you can leverage ChatGPT conversational capabilities and Consensus database of studies.
• Regular price is 9$ with a 40% student discount or 30% with the “Effortless30” code. Searches are always free, and the AI analysis is what you are paying for. Twenty uses of AI are free per month.

Consensus is featured as part of my literature Review webinar and you can get a recording here:

Leverage semantic and citation search with AI to find the most impactful literature quickly. Uncover reference gaps combining multiple tools.  Use ChatGPT assistants to get rid of hallucinations and use AI to aid faithfully and ethically in your lit review and writing process.

How To Write A Research Proposal With AI

To write a research paper using A.I., define your research topic and formulate straightforward, specific research questions, use A.I. to streamline the literature reviews, refine methodologies, and create a structured proposal outline, draft your proposal using the outline you created. Use an A.I. writing assistant for revision, correcting errors, and enhancing clarity; incorporate visual aids to show critical concepts effectively. As such, define your research topic and formulate straightforward, specific research questions. Use AI to streamline the literature reviews, refine methodologies, and create a structured proposal outline. Draft your proposal using the outline you created. Use an AI writing assistant for revision, correcting errors, and enhancing clarity.

Fredrick Eghosa

May 21, 2024

Table of Contents

Key Takeaways

Understanding the research proposal and its components, introduction:, literature review:, research objectives:, methodology:, significance and contributions:, budget (if applicable):, references:, how to write a research proposal using a.i.:, define your research topic, formulate research questions, consider the types of research questions you want to use, characteristics of practical research questions you must keep in mind, how to structure your research questions, conduct a comprehensive literature review, develop a research proposal outline, refine your methodology, don't forget to include visual aids., draft and revise your proposal, wrapping up.

• A research proposal provides a detailed plan for a research project. It presents your proposed study's objectives, methodology, and potential contribution.
• A research proposal usually includes a title, abstract, literature review, research objectives, methodology, significance and contribution, timeline, budget, and references.
• Writing a research paper using A.I. involves defining your research topic and formulating straightforward, specific research questions. Use CoWriter to streamline literature reviews, refine methodologies, and create a structured proposal outline. Write your proposal and use CoWriter to correct errors and enhance clarity.

• Use Interrogative Language. Begin questions with "What," "How," "Why," or "To what extent" to prompt investigation.
• Avoid Yes/No Questions. Formulate questions that require detailed responses and deeper exploration.

• Start by Determining the scope of your review (e.g., timeframe, geographical focus, key concepts) to ensure relevance. Then, Identify relevant keywords, synonyms, and phrases related to your research topic.
• Explore library catalogs and repositories for books, theses, dissertations, and other publications related to your topic.
• When reviewing the literature, applying filters (e.g., publication date, study design, language) will help you narrow search results and focus on high-quality sources.
• Select literature that directly addresses your research questions or contributes significantly to understanding your topic.
• Identify gaps or limitations in existing literature that highlight the need for your research.

• Familiarize yourself with research designs such as experimental, observational, qualitative, quantitative, or mixed-methods.
• Select the most appropriate research design based on your research questions, objectives, and available resources.
• Discuss the advantages and limitations of the chosen design and explain why it is suitable for your study.
• Describe the methods you will use to collect data (e.g., surveys, interviews, observations, experiments).
• Explain how you will develop or adapt data collection instruments (e.g., questionnaires, interview guides, observation protocols).
• Specify the target population and describe the sampling frame (e.g., random, purposive, convenience).
• Discuss ethical issues regarding participant recruitment, data collection, and privacy protection.
• Mention any software tools you will use for data analysis and explain why they are appropriate for your study.
• Ensure that your methodology aligns with the research objectives and aims to answer the research questions effectively.
• Please provide a clear rationale for each methodological choice and explain how it contributes to achieving the study's goals.

Join other 3200+ writers now!

Ready to take the next big step for your writing?

Lead engineering teams at Figma, Pitch, and Protocol Labs.

Related posts

How To Write A Research Paper With AI

To write a research paper, ensure you understand the assignment, choose an engaging topic, conduct thorough research, develop a clear thesis statement, and create a structured outline. Write while integrating research findings, then revise for clarity and coherence. Finally, edit for accuracy and adhere to formatting guidelines to present a polished and professional paper. You can use an A.I. writing assistant to optimize and streamline entire writing.

Apr 16, 2024

The Best Free AI MLA Citation Generator

The best free AI MLA citation generators are CoWriter, Opendemia, Scribbr MLA Citation Generator, MyBib, Citefast, Cite This For Me's MLA Citation Generator, and QuillBot M.L.A. Citation Generator. They stay updated on the latest MLA guidelines and can handle various source types like books, articles, and websites.

The Best Free Outline Generator for Essays

The best free outline generators for essay writing are CoWriter, Ahrefs Free AI Outline Generator, ClickUp, Jenni AI Essay Outline Generator, GitMind, Rytr, and Simplified. They streamline the process by generating structured outlines based on prompts and parameters.

Apr 12, 2024

The Best Free AI APA Citation Generator

The best free AI APA citation generators are CoWriter, Grammarly, SciSpace APA Citation Generator, Scribbr AI Citation Generators, Quillbot AI Citation Generators, Junia.ai, and Simplified. These generators use intelligent algorithms to automatically create citations for different sources, saving time and ensuring formatting and APA citation style accuracy.

How is a narrative essay organized?

A narrative essay tells a story chronologically, beginning with an introduction, moving into a body where events build to a climax, and finishing with a resolution or final reflection.

Mar 16, 2024

10 Best AI Co-Writers

The best AI co-writers are CoWriter, HIX.AI, Copy.ai, Wordtune, Scalenut, Rytr, HyperWrite, Texta, TextCortex, and Writesonic. They can help generate ideas, overcome writer's block, and improve the flow of your writing.

Mar 18, 2024

How to Edit an Essay Written by AI to Perfection

To edit an AI-written essay perfectly, carefully read the text to ensure it makes sense and conveys your ideas. Please review the entire piece to grasp its tone, purpose, and quality, as AI-generated content often lacks logical progression and may have gaps, awkward transitions, or readability issues.

Mar 24, 2024

10 Steps to Writing an Informative Essay with an Outline

To write an informative essay with an outline, pick a topic, research it, and create an outline. Write an introduction with a hook and thesis, followed by body paragraphs with evidence. Conclude by summarizing the main points and restating the thesis. Finally, edit, cite sources, and submit.

Mar 25, 2024

Jenni AI Review and Best Alternatives

Jenni.AI is an AI writer designed to assist with academic research and writing. It offers a great selection of features for academic purposes, including a built-in research engine. The best alternatives for Jenni AI you can try are CoWriter, Jasper AI, Copy AI, Frase.io, and Writesonic.

Mar 27, 2024

How to Write a Biography Essay and Biography Essay Examples

To write a biography essay, choose an exciting subject, research extensively, and develop a thesis statement. Then, structure your essay chronologically or thematically, starting with a captivating introduction, exploring the subject's life in the body paragraphs, and concluding with its contemporary significance.

The Good AI Review and Best Alternatives

Good AI is a handy platform that uses smart technology to assist with writing tasks. Its AI essay writer lets users quickly create 1,500-word, well-structured, and informative essays.

How to Write a Biography Essay With Examples

30 AI Prompts to Humanize Your Essay

AI prompts to humanize your essay are invaluable tools for students who want to humanize their AI-generated essays. With prompts for different writing styles and objectives, you can add personality, storytelling, humor, and clarity to their content.

The 7 Best AI Bibliography Generator

The best AI bibliography generators are CoWriter, Zotero, EndNote, Cite This For Me, Citation Machine, CiteMaker, and KnightCite. These tools streamline the citation process by supporting various citation styles, source types, and formatting options, ensuring accuracy and adherence to academic standards.

May 20, 2024

10 Literary Analysis Essay Examples

To write a literary analysis essay always understand the assignment thoroughly and identify the key elements e.g. plot, characters, and themes. Select a central theme to focus on and put together evidence to support your analysis.

The 5 Best AI Writer for Students

The best AI writers for students are CoWriter, Jasper, AI-Writer, Rytr, and Article Forge. Choosing the best AI writer for students depends on their needs. Some prioritize grammar and clarity assistance, while others focus on paraphrasing and summarizing.

Best Free AI Paper Writer

The best free AI paper writers are CoWriter, Rytr, Simplified, CopyAI, Writesonic, Grammarly, and Paperpal. These tools can help you brainstorm or start and polish your paper.

Mar 11, 2024

5 Best AI Writer for Research Papers

The best AI writers for research papers are CoWriter, SciSpace Literature Review, Wordtune, Trinka, and Paperpal. These AI writers offer different functionalities, from grammar and citation checking to plagiarism detection and content generation.

Can AI Write An Annotated Bibliography

A.I. can write an annotated bibliography by curating and organizing relevant sources. It can generate concise summaries that outline each source's content, relevance, and significance to your research. A.I. writing assistant streamlines the process of compiling an annotated bibliography, saving time and effort while ensuring the inclusion of informative annotations for each source.

How To Write A Historical Essay Introduction

To write a historical essay introduction, begin with an engaging hook, like a thought-provoking quote or a question. Follow this with background details about your topic and conclude with a clear thesis statement. Utilize CoWriter to assist in composing your introduction.

How To Write a 4-Paragraph Essay

To write a 4-paragraph essay effectively, start by thoroughly researching your topic. This step is crucial for gathering supporting information. Next, create a structured outline that divides your essay into four clear paragraphs. Draft your thesis statement to convey the topic of your essay. With the outline in place, draft your essay following the outlined structure. Finally, take time to edit and proofread your essay.

How To Write A Curatorial Statement With AI

To write a curatorial statement with AI, begin by conducting thorough research into the historical context of your exhibition and the backgrounds of the artworks, including their styles and mediums. Develop a clear and concise outline to structure your statement effectively. Write the content of your statement and edit it for clarity and correctness. Use CoWriter to streamline and enhance the entire writing and editing process.

AI-assisted writing is quietly booming in academic journals. Here’s why that’s OK

Lecturer in Bioethics, Monash University & Honorary fellow, Melbourne Law School, Monash University

Disclosure statement

Julian Koplin does not work for, consult, own shares in or receive funding from any company or organisation that would benefit from this article, and has disclosed no relevant affiliations beyond their academic appointment.

Monash University provides funding as a founding partner of The Conversation AU.

View all partners

If you search Google Scholar for the phrase “ as an AI language model ”, you’ll find plenty of AI research literature and also some rather suspicious results. For example, one paper on agricultural technology says:

As an AI language model, I don’t have direct access to current research articles or studies. However, I can provide you with an overview of some recent trends and advancements …

Obvious gaffes like this aren’t the only signs that researchers are increasingly turning to generative AI tools when writing up their research. A recent study examined the frequency of certain words in academic writing (such as “commendable”, “meticulously” and “intricate”), and found they became far more common after the launch of ChatGPT – so much so that 1% of all journal articles published in 2023 may have contained AI-generated text.

(Why do AI models overuse these words? There is speculation it’s because they are more common in English as spoken in Nigeria, where key elements of model training often occur.)

The aforementioned study also looks at preliminary data from 2024, which indicates that AI writing assistance is only becoming more common. Is this a crisis for modern scholarship, or a boon for academic productivity?

Who should take credit for AI writing?

Many people are worried by the use of AI in academic papers. Indeed, the practice has been described as “ contaminating ” scholarly literature.

Some argue that using AI output amounts to plagiarism. If your ideas are copy-pasted from ChatGPT, it is questionable whether you really deserve credit for them.

But there are important differences between “plagiarising” text authored by humans and text authored by AI. Those who plagiarise humans’ work receive credit for ideas that ought to have gone to the original author.

By contrast, it is debatable whether AI systems like ChatGPT can have ideas, let alone deserve credit for them. An AI tool is more like your phone’s autocomplete function than a human researcher.

The question of bias

Another worry is that AI outputs might be biased in ways that could seep into the scholarly record. Infamously, older language models tended to portray people who are female, black and/or gay in distinctly unflattering ways, compared with people who are male, white and/or straight.

This kind of bias is less pronounced in the current version of ChatGPT.

However, other studies have found a different kind of bias in ChatGPT and other large language models : a tendency to reflect a left-liberal political ideology.

Any such bias could subtly distort scholarly writing produced using these tools.

The hallucination problem

The most serious worry relates to a well-known limitation of generative AI systems: that they often make serious mistakes.

For example, when I asked ChatGPT-4 to generate an ASCII image of a mushroom, it provided me with the following output.

It then confidently told me I could use this image of a “mushroom” for my own purposes.

These kinds of overconfident mistakes have been referred to as “ AI hallucinations ” and “ AI bullshit ”. While it is easy to spot that the above ASCII image looks nothing like a mushroom (and quite a bit like a snail), it may be much harder to identify any mistakes ChatGPT makes when surveying scientific literature or describing the state of a philosophical debate.

Unlike (most) humans, AI systems are fundamentally unconcerned with the truth of what they say. If used carelessly, their hallucinations could corrupt the scholarly record.

Should AI-produced text be banned?

One response to the rise of text generators has been to ban them outright. For example, Science – one of the world’s most influential academic journals – disallows any use of AI-generated text .

I see two problems with this approach.

The first problem is a practical one: current tools for detecting AI-generated text are highly unreliable. This includes the detector created by ChatGPT’s own developers, which was taken offline after it was found to have only a 26% accuracy rate (and a 9% false positive rate ). Humans also make mistakes when assessing whether something was written by AI.

It is also possible to circumvent AI text detectors. Online communities are actively exploring how to prompt ChatGPT in ways that allow the user to evade detection. Human users can also superficially rewrite AI outputs, effectively scrubbing away the traces of AI (like its overuse of the words “commendable”, “meticulously” and “intricate”).

The second problem is that banning generative AI outright prevents us from realising these technologies’ benefits. Used well, generative AI can boost academic productivity by streamlining the writing process. In this way, it could help further human knowledge. Ideally, we should try to reap these benefits while avoiding the problems.

The problem is poor quality control, not AI

The most serious problem with AI is the risk of introducing unnoticed errors, leading to sloppy scholarship. Instead of banning AI, we should try to ensure that mistaken, implausible or biased claims cannot make it onto the academic record.

After all, humans can also produce writing with serious errors, and mechanisms such as peer review often fail to prevent its publication.

We need to get better at ensuring academic papers are free from serious mistakes, regardless of whether these mistakes are caused by careless use of AI or sloppy human scholarship. Not only is this more achievable than policing AI usage, it will improve the standards of academic research as a whole.

This would be (as ChatGPT might say) a commendable and meticulously intricate solution.

• Artificial intelligence (AI)
• Academic journals
• Academic publishing
• Hallucinations
• Scholarly publishing
• Academic writing
• Large language models
• Generative AI

Lecturer / Senior Lecturer - Marketing

Case Management Specialist

Assistant Editor - 1 year cadetship

Executive Dean, Faculty of Health

Lecturer/Senior Lecturer, Earth System Science (School of Science)

The four best AI writing apps worth a try

Suswati Basu is a multilingual, award-winning editor and the founder of the intersectional literature channel, How To Be Books. She was shortlisted for the Guardian…

AI tools like ChatGPT are revolutionizing writing, aiding in document creation and streamlining work processes.

Human oversight remains crucial to ensure accuracy and prevent AI-generated content from being too generic or erroneous.

Various AI writing apps, such as Copy.ai, Anyword, Writesonic, and Rytr, offer different features and pricing plans to cater to diverse needs.

Whatever the industry, more and more people are using artificial intelligence to assist with their work, especially since the launch of ChatGPT . Many workers and students now use the tool to write documents, essays, and more. It often speeds up the process of creating content and managing the mundane aspects of work. While they aren’t taking over the world yet, they are quickly evolving and have reached a stage where they can be useful, at least in the right circumstances.

Of course, all AI writing software requires some level of human oversight to achieve the best results. Without it, the software can generate content that is rather generic or even hallucinate facts , even though it may appear to be written by a human. As AI tools gain popularity, people are becoming more adept at recognizing the often bland nature of AI-generated content and are likely to either identify it or at least be suspicious of content that seems to lack a human touch.

How do AI writing tools work?

Predictive text on a smartphone or keyboard works in a similar way to AI. It essentially provides an “educated” guess as to what a user might say next based on their history of typing in a specific app. The difference is that it will rely on what other people have said as well, and find some level of commonality.

For example, if typing the sentence “The cat sat on the,” the model predicts the word “mat” based on the input sequence. It’s a simplistic illustration, but in reality, the model considers a vast number of possible continuations based on its training data and selects the most likely one.

Some large language models (LLMs) now use internet searches to gather information relevant to their writing prompts, which they then integrate into their responses. While earlier versions tended to produce stiff and robotic output, developments in algorithms and programming have allowed AI writers to produce more human-like responses. These days, most are using OpenAI’s ChatGPT models to power their tools.

Which is the best free AI app for writing?

ReadWrite decided to ask AI itself for a text prompt to assess how well it would fare:

Write a 250-word short story about a character who discovers a hidden world within their favorite childhood book. The story should include:

• A vivid description of the hidden world, including its unique features and inhabitants.
• The character’s emotional journey as they explore this new world and confront their own nostalgia.
• A surprising twist or revelation that changes their perspective on the book and their childhood.

Copy.ai ’s free trial uses ChatGPT-3.5, hence it is limited in terms of vocabulary and sophistication. Using the given prompt, it managed to create a story about a woman named Evelyn who discovered a magical library hidden in a garden.

While the story was quite pleasant to read, several noticeable AI traits appeared. For one, it used the main character’s name in every paragraph. Several words seem to be commonly used by ChatGPT, such as “nostalgia,” “abundance,” and “vibrant.” Combined with the repetitiveness, it seemed rather obvious that AI was used.

The pro version of Copy.ai uses ChatGPT-4, so it may produce better results. It’s unclear whether the app will incorporate new versions of the LLM, as OpenAI’s CEO Sam Altman revealed that ChatGPT-5 is on its way.

Copy.ai is also compatible with a variety of other AI models including Azure and Anthropic , which makes it more flexible for delivering results. Another piece of good news is that the company has a zero-retention data policy.

Like OpenAI, Copy.ai has a free version with limited words, while the Pro version starts from $36 per month for five users, and has unlimited capacity.

Anyword is a little bit more complicated to use as it doesn’t bring the user directly to the writing app. It offers a variety of writing options, including 1,000-word SEO-friendly blog articles, social media posts, and ad campaigns. If you just need a simple text prompt box, you can find it under “general prompt” on the dashboard.

However, it allows you to change the tone of voice from neutral to rebellious, or even to a multi-tonal style incorporating three dimensions. There is also the capability to target specific audiences, whether they are nostalgic readers or creative writers. When kept neutral with a broad audience, it produced a similar copy, characterized by the repetition of names and overly flowery language. Nevertheless, the story was creative but seemed to heavily favor the fantasy genre.

Using other filters, it generated a tale almost identical to the first, including the same phrases such as “The Enchanted Forest,” “newfound,” “intertwining,” and “grandmother.” It’s quite apparent that it has a defined notion of what constitutes a childhood book.

The Starter plan with one seat costs $39 per month paid annually. The Data-Driven plan costs $79/month, and the Business plan is $349 per month.

Writesonic is another free AI writing tool, with an interface comparable to ChatGPT as it has a dark left-hand side panel. Like Copy.ai, the unpaid version is powered by ChatGPT-3.5 among others, but has better billing options than OpenAI. The company states that it is “agnostic” about using a variety of LLMs.

“Our proprietary AI Model Gateway, called GPT Router dynamically routes between multiple AI models, thus speeding up responses and ensuring the best quality output as well as non-stop reliability,” it says on its website. These include Meta’s LLama and Google’s Gemini models.

The AI article writer can create long-form content pieces and includes a chatbot assistant named Chatsonic. When tested with a text prompt, it produced a slightly more imaginative story, making it more reliable than other tools.

Although there is a free version, Chatsonic costs $12 per month when paid annually and claims to offer output quality comparable to GPT-4 and Claude 3 Opus . The individual plan costs $16 and includes additional features such as an SEO optimizer, plagiarism checker, and a tool for facts and citations.

Rytr , with a name that phonetically resembles “writer,” adopts a no-nonsense approach by featuring a straightforward interface like that of a writing pad. That being said, it still allows users to select the tone and use case of the output. Using the “story plot” function, it produced a tale almost identical to one by Anyword.

Not only did “Amelia” have a copy of “The Enchanted Forest,” but she also showed a penchant for streams and creeks. Hence, it is obvious that Rytr also uses ChatGPT-3 for its content writing.

Rytr is free to use, with unlimited queries available for $7.50 per month. In comparison, ChatGPT-4 costs $20 per month currently. The difference is that Rytr offers other features such as a plagiarism checker and SEO toolkit.

Featured image: Canva

About ReadWrite’s Editorial Process

The ReadWrite Editorial policy involves closely monitoring the tech industry for major developments, new product launches, AI breakthroughs, video game releases and other newsworthy events. Editors assign relevant stories to staff writers or freelance contributors with expertise in each particular topic area. Before publication, articles go through a rigorous round of editing for accuracy, clarity, and to ensure adherence to ReadWrite's style guidelines.

Suswati Basu Tech journalist

Suswati Basu is a multilingual, award-winning editor and the founder of the intersectional literature channel, How To Be Books. She was shortlisted for the Guardian Mary Stott Prize and longlisted for the Guardian International Development Journalism Award. With 18 years of experience in the media industry, Suswati has held significant roles such as head of audience and deputy editor for NationalWorld news, digital editor for Channel 4 News and ITV News. She has also contributed to the Guardian and received training at the BBC As an audience, trends, and SEO specialist, she has participated in panel events alongside Google. Her…

Related News

How AI Is Increasing the Personalization of Marketing Strategies

Dutch researchers launch — oh, really? — an AI sarcasm detector

IMF chief warns of AI “tsunami” facing six in 10 jobs

What is Character.AI? How to create your own chatbots and use the old version

Two US states seize the initiative to regulate AI

Most popular tech stories.

• US inches closer to a TikTok ban
• EA revealed how much Apex Legends has made and…it’s a lot
• Minecraft player has X-Files moment as they report an in-game UFO sighting
• Dogecoin Maxi DonAlt Posts $1 Price Prediction – Risk On For Meme Coins?
• Beautiful flying adventure Kid Pilot set to hit Steam VR later this month

Latest News

Call of Duty deleted post-credit scene implies darker ending to a classic trilogy

A Call of Duty modder has purportedly found a post-credits scene to the original Call of Duty: Modern Warfare 3 that changes the game’s narrative, based on its interpretation. It’s...

Rumor says new Xbox hardware is coming in 2026

Atari confirms release date and details for arcade racer NeoSprint

Industry report cites deepfakes as second most common security concern

MultiVersus adds The Matrix and Friday the 13th villains to roster for May 28 release

Popular topics, get the biggest tech headlines of the day delivered to your inbox.

By signing up, you agree to our Terms and Privacy Policy. Unsubscribe anytime.

Explore the latest in tech with our Tech News. We cut through the noise for concise, relevant updates, keeping you informed about the rapidly evolving tech landscape with curated content that separates signal from noise.

Explore tech impact in In-Depth Stories. Narrative data journalism offers comprehensive analyses, revealing stories behind data. Understand industry trends for a deeper perspective on tech's intricate relationships with society.

Empower decisions with Expert Reviews, merging industry expertise and insightful analysis. Delve into tech intricacies, get the best deals, and stay ahead with our trustworthy guide to navigating the ever-changing tech market.