search research papers using ai

A free, AI-powered research tool for scientific literature

• Sara Goldrick-Rab

New & Improved API for Developers

Introducing semantic reader in beta.

Stay Connected With Semantic Scholar Sign Up What Is Semantic Scholar? Semantic Scholar is a free, AI-powered research tool for scientific literature, based at the Allen Institute for AI.

Analyze research papers at superhuman speed

Search for research papers, get one sentence abstract summaries, select relevant papers and search for more like them, extract details from papers into an organized table.

Find themes and concepts across many papers

Don't just take our word for it.

Tons of features to speed up your research

Upload your own pdfs, orient with a quick summary, view sources for every answer, ask questions to papers, research for the machine intelligence age, pick a plan that's right for you, get in touch, enterprise and institutions, custom pricing, common questions. great answers., how do researchers use elicit.

Over 2 million researchers have used Elicit. Researchers commonly use Elicit to:

• Speed up literature review
• Find papers they couldn’t find elsewhere
• Automate systematic reviews and meta-analyses
• Learn about a new domain

Elicit tends to work best for empirical domains that involve experiments and concrete results. This type of research is common in biomedicine and machine learning.

What is Elicit not a good fit for?

Elicit does not currently answer questions or surface information that is not written about in an academic paper. It tends to work less well for identifying facts (e.g. “How many cars were sold in Malaysia last year?”) and theoretical or non-empirical domains.

What types of data can Elicit search over?

Elicit searches across 125 million academic papers from the Semantic Scholar corpus, which covers all academic disciplines. When you extract data from papers in Elicit, Elicit will use the full text if available or the abstract if not.

How accurate are the answers in Elicit?

A good rule of thumb is to assume that around 90% of the information you see in Elicit is accurate. While we do our best to increase accuracy without skyrocketing costs, it’s very important for you to check the work in Elicit closely. We try to make this easier for you by identifying all of the sources for information generated with language models.

What is Elicit Plus?

Elicit Plus is Elicit's subscription offering, which comes with a set of features, as well as monthly credits. On Elicit Plus, you may use up to 12,000 credits a month. Unused monthly credits do not carry forward into the next month. Plus subscriptions auto-renew every month.

What are credits?

Elicit uses a credit system to pay for the costs of running our app. When you run workflows and add columns to tables it will cost you credits. When you sign up you get 5,000 credits to use. Once those run out, you'll need to subscribe to Elicit Plus to get more. Credits are non-transferable.

How can you get in contact with the team?

Please email us at [email protected] or post in our Slack community if you have feedback or general comments! We log and incorporate all user comments. If you have a problem, please email [email protected] and we will try to help you as soon as possible.

What happens to papers uploaded to Elicit?

When you upload papers to analyze in Elicit, those papers will remain private to you and will not be shared with anyone else.

How accurate is Elicit?

Training our models on specific tasks, searching over academic papers, making it easy to double-check answers, save time, think more. try elicit for free..

The best AI tools for research papers and academic research (Literature review, grants, PDFs and more)

As our collective understanding and application of artificial intelligence (AI) continues to evolve, so too does the realm of academic research. Some people are scared by it while others are openly embracing the change. 

Make no mistake, AI is here to stay!

Instead of tirelessly scrolling through hundreds of PDFs, a powerful AI tool comes to your rescue, summarizing key information in your research papers. Instead of manually combing through citations and conducting literature reviews, an AI research assistant proficiently handles these tasks.

These aren’t futuristic dreams, but today’s reality. Welcome to the transformative world of AI-powered research tools!

This blog post will dive deeper into these tools, providing a detailed review of how AI is revolutionizing academic research. We’ll look at the tools that can make your literature review process less tedious, your search for relevant papers more precise, and your overall research process more efficient and fruitful.

I know that I wish these were around during my time in academia. It can be quite confronting when trying to work out what ones you should and shouldn’t use. A new one seems to be coming out every day!

Here is everything you need to know about AI for academic research and the ones I have personally trialed on my YouTube channel.

My Top AI Tools for Researchers and Academics – Tested and Reviewed!

There are many different tools now available on the market but there are only a handful that are specifically designed with researchers and academics as their primary user.

These are my recommendations that’ll cover almost everything that you’ll want to do:

Want to find out all of the tools that you could use?

Here they are, below:

AI literature search and mapping – best AI tools for a literature review – elicit and more

Harnessing AI tools for literature reviews and mapping brings a new level of efficiency and precision to academic research. No longer do you have to spend hours looking in obscure research databases to find what you need!

AI-powered tools like Semantic Scholar and elicit.org use sophisticated search engines to quickly identify relevant papers.

They can mine key information from countless PDFs, drastically reducing research time. You can even search with semantic questions, rather than having to deal with key words etc.

With AI as your research assistant, you can navigate the vast sea of scientific research with ease, uncovering citations and focusing on academic writing. It’s a revolutionary way to take on literature reviews.

• Elicit –  https://elicit.org
• Litmaps –  https://www.litmaps.com
• Research rabbit – https://www.researchrabbit.ai/
• Connected Papers –  https://www.connectedpapers.com/
• Supersymmetry.ai: https://www.supersymmetry.ai
• Semantic Scholar: https://www.semanticscholar.org
• Laser AI –  https://laser.ai/
• Inciteful –  https://inciteful.xyz/
• Scite –  https://scite.ai/
• System –  https://www.system.com

If you like AI tools you may want to check out this article:

• How to get ChatGPT to write an essay [The prompts you need]

AI-powered research tools and AI for academic research

AI research tools, like Concensus, offer immense benefits in scientific research. Here are the general AI-powered tools for academic research. 

These AI-powered tools can efficiently summarize PDFs, extract key information, and perform AI-powered searches, and much more. Some are even working towards adding your own data base of files to ask questions from. 

Tools like scite even analyze citations in depth, while AI models like ChatGPT elicit new perspectives.

The result? The research process, previously a grueling endeavor, becomes significantly streamlined, offering you time for deeper exploration and understanding. Say goodbye to traditional struggles, and hello to your new AI research assistant!

• Consensus –  https://consensus.app/
• Iris AI –  https://iris.ai/
• Research Buddy –  https://researchbuddy.app/
• Mirror Think – https://mirrorthink.ai

AI for reading peer-reviewed papers easily

Using AI tools like Explain paper and Humata can significantly enhance your engagement with peer-reviewed papers. I always used to skip over the details of the papers because I had reached saturation point with the information coming in. 

These AI-powered research tools provide succinct summaries, saving you from sifting through extensive PDFs – no more boring nights trying to figure out which papers are the most important ones for you to read!

They not only facilitate efficient literature reviews by presenting key information, but also find overlooked insights.

With AI, deciphering complex citations and accelerating research has never been easier.

• Aetherbrain – https://aetherbrain.ai
• Explain Paper – https://www.explainpaper.com
• Chat PDF – https://www.chatpdf.com
• Humata – https://www.humata.ai/
• Lateral AI –  https://www.lateral.io/
• Paper Brain –  https://www.paperbrain.study/
• Scholarcy – https://www.scholarcy.com/
• SciSpace Copilot –  https://typeset.io/
• Unriddle – https://www.unriddle.ai/
• Sharly.ai – https://www.sharly.ai/
• Open Read –  https://www.openread.academy

AI for scientific writing and research papers

In the ever-evolving realm of academic research, AI tools are increasingly taking center stage.

Enter Paper Wizard, Jenny.AI, and Wisio – these groundbreaking platforms are set to revolutionize the way we approach scientific writing.

Together, these AI tools are pioneering a new era of efficient, streamlined scientific writing.

• Jenny.AI – https://jenni.ai/ (20% off with code ANDY20)
• Yomu – https://www.yomu.ai
• Wisio – https://www.wisio.app

AI academic editing tools

In the realm of scientific writing and editing, artificial intelligence (AI) tools are making a world of difference, offering precision and efficiency like never before. Consider tools such as Paper Pal, Writefull, and Trinka.

Together, these tools usher in a new era of scientific writing, where AI is your dedicated partner in the quest for impeccable composition.

• PaperPal –  https://paperpal.com/
• Writefull –  https://www.writefull.com/
• Trinka –  https://www.trinka.ai/

AI tools for grant writing

In the challenging realm of science grant writing, two innovative AI tools are making waves: Granted AI and Grantable.

These platforms are game-changers, leveraging the power of artificial intelligence to streamline and enhance the grant application process.

Granted AI, an intelligent tool, uses AI algorithms to simplify the process of finding, applying, and managing grants. Meanwhile, Grantable offers a platform that automates and organizes grant application processes, making it easier than ever to secure funding.

Together, these tools are transforming the way we approach grant writing, using the power of AI to turn a complex, often arduous task into a more manageable, efficient, and successful endeavor.

• Granted AI – https://grantedai.com/
• Grantable – https://grantable.co/

Best free AI research tools

There are many different tools online that are emerging for researchers to be able to streamline their research processes. There’s no need for convience to come at a massive cost and break the bank.

The best free ones at time of writing are:

• Elicit – https://elicit.org
• Connected Papers – https://www.connectedpapers.com/
• Litmaps – https://www.litmaps.com ( 10% off Pro subscription using the code “STAPLETON” )
• Consensus – https://consensus.app/

Wrapping up

The integration of artificial intelligence in the world of academic research is nothing short of revolutionary.

With the array of AI tools we’ve explored today – from research and mapping, literature review, peer-reviewed papers reading, scientific writing, to academic editing and grant writing – the landscape of research is significantly transformed.

The advantages that AI-powered research tools bring to the table – efficiency, precision, time saving, and a more streamlined process – cannot be overstated.

These AI research tools aren’t just about convenience; they are transforming the way we conduct and comprehend research.

They liberate researchers from the clutches of tedium and overwhelm, allowing for more space for deep exploration, innovative thinking, and in-depth comprehension.

Whether you’re an experienced academic researcher or a student just starting out, these tools provide indispensable aid in your research journey.

And with a suite of free AI tools also available, there is no reason to not explore and embrace this AI revolution in academic research.

We are on the precipice of a new era of academic research, one where AI and human ingenuity work in tandem for richer, more profound scientific exploration. The future of research is here, and it is smart, efficient, and AI-powered.

Before we get too excited however, let us remember that AI tools are meant to be our assistants, not our masters. As we engage with these advanced technologies, let’s not lose sight of the human intellect, intuition, and imagination that form the heart of all meaningful research. Happy researching!

Thank you to Ivan Aguilar – Ph.D. Student at SFU (Simon Fraser University), for starting this list for me!

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

AI Search Engine for Research

Find & understand the best science, faster.

Try an example search

See how it works

Used by researchers at the world’s top institutes

Why Consensus?

Consensus responsibly uses AI to help you conduct research faster.

Extensive research coverage

Search through over 200M research papers in every domain of science & academia.

Time-saving AI insights

Gain insight faster with our Copilot and Consensus Meter. We leverage both OpenAI & custom LLMs.

Find the most relevant papers

Our proprietary academic search tools & filters mean you’ll find the very best science for your query.

Results connected to science

We cite every source. You're always only a click away from the underlying research paper.

Who Consensus helps most...

Anyone with curiosity. Whether you’re conducting research or just fact-checking a friend, if you need answers from the literature, Consensus is for you.

Students & researchers

Streamline your literature review process. Quickly see the direction of current findings, and surface the best papers.

Science organizations

Quickly check ingredients, chemicals, or molecules. Understand mechanisms of action, and stay up to date with new research.

Clinicians & doctors

Get answers to patients’ questions that you can trust, share information they can digest, and easily cite your references.

Universities & schools

Students & researchers at over 5,000 universities worldwide search with Consensus. We partner with libraries, higher learning institutes, and universities.

Writers & journalists

Source evidence-based insights on your topic, understand connected fields, and see related suggested searches.

Health & fitness experts

Easily check out the science regarding supplement safety, diet types, and exercise science outcomes.

1,000,000 +

Researchers, students, doctors, professionals, and evidence-based humans choose Consensus.

"It's not every day I find a tool that truly helps with my work. Consensus blew me away when I started using it, I was learning things I had never encountered before. This is an AI product that isn't hype."

"I can make sense of what’s out there a lot faster with Consensus. I jump into different topics with the summary & Copilot before diving deeper. The interface makes it so easy to review individual papers and see what they’re about."

"You no longer need to read countless papers to find the answer you need. Simply ask a question and Consensus gives you AI-powered summaries of the top 5-10 articles"

Consensus has been featured in

Consensus vs ChatGPT

ChatGPT predicts the most likely language that should follow. Consensus helps you find & understand the best science, faster.

Results directly connected to scientific papers

Fully machine-generated, prone to hallucinations

Consensus academic features

Consensus Meter

Quickly see the scientific consensus & gain topic context and direction. See exactly which papers were included.

Simply include in your search - ask Copilot to adopt a style, draft content, format, create lists, and more. Read a referenced topic synthesis.

Paper-level Insights

We extract key insights and answers. Locate the most helpful papers and digest their insights faster.

Search Filters

Filter by sample size, study design, methodology, if the paper is open access, a human or animal study (and many more filters).

Quality Indicators

Focus on the best papers - intuitive labels for citations, journal quality, and study type.

Study Snapshot

Our Study Snapshot quickly shows key information like Population, Sample size, Methods, etc. - all within the results page.

How we created the ultimate search engine for science

Search: Find the best papers

Purpose-built academic & vector search functionality. Consensus utilizes important factors like study design, sample size, population details, and more to rank the best research higher.

Dedicated research LLMs

Our proprietary LLMs read research like an expert - we also leverage the best-in-class models from OpenAI. Consensus generates AI insights at both the search and paper level.

• 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 Translation to put a text or search results into another language.
• Upload a PDF document and let Paper Espresso 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: Jun 5, 2024 12:37 PM
• URL: https://tamu.libguides.com/c.php?g=1289555

10 Best AI Tools for Academic Research in 2024 (Free and Paid)

Ayush Chaturvedi

20 min read

Research can be a time-consuming endeavour. Sifting through mountains of literature, analyzing data, and crafting clear arguments can feel overwhelming. 

However, you can streamline much of this research process with Artificial Intelligence (AI) tools, some of which are the best for research.

These AI-powered assistants can search vast databases in seconds, pinpoint relevant studies, and customize data to your specific research question. 

They can also recommend key research articles and highlight emerging trends within your field, saving you time.

Additionally, with the help of the best AI tools for research, you can improve your writing and streamline your workflow with real-time grammar and punctuation checks, stylistic suggestions, and clear explanations of complex concepts.

But how do you choose?

Don't worry; we've got you covered. 

We have created a list of all the best AI tools for research on the internet, filtering based on various factors and handpicked the top 10. 

These research AI tools not only assist you in research but also integrate with your workflow and reduce your overall workload. 

So let's get started.

Best AI Tools for Research at a Glance

What are research ai tools, benefits of using ai tools for research, factors to consider when choosing the best ai tools for research, top 10 best ai tools for research, key features of elephas , elephas pricing , elepahs reviews, chatgpt key features , chatgpt pricing , chatgpt reviews , typeset.io features:, typeset.io pricing , typeset.io reviews , quillbot key features , quillbot pricing , quillbot review , wordvice.ai features:, wordvice.ai pricing , wordvice.ai reviews , consensus ai key features , consensus ai pricing , consensus ai reviews , scite.ai features , scite.ai pricing , scite.ai reviews , scholarly key features, scholarcy pricing , scholarcy reviews , proofhub key features , proofhub pricing , proofhub reviews , research rabbit key features , research rabbit pricing , research rabbit reviews , limitations of ai tools for research, case study: how a professor used elephas in his lesson research process.

• Conclusion 

1. Which AI is better for research?

2. is chatgpt good for research, 3. how can ai be used for research, 4. what is the best ai for phd.

Elephas: Summarize research, rewrite content in different styles, and organize summaries in a central "Super Brain" for easy access.

ChatGPT: Summarize news articles and answer research questions

Typeset.io: Streamline academic writing with templates and citation management. 

Quillbot: Rephrase text and summarize complex materials for research. 

Wordvice.ai : Ensure clarity, grammar, and originality in your academic writing.

Consensus AI: Search vast databases and filter research papers for quality.

Scite.ai: Get real citations and measure the credibility of research claims.

Scholarcy: Summarize complex articles and build a searchable research library.

ProofHub: Manage research projects with tasks, collaboration tools, and scheduling.

ResearchRabbit: Build a research library and get recommendations for new papers. 

Research AI tools are game-changers for students, academics, and researchers, streamlining the entire research process. 

With the help of the best AI tools for research as your personal research assistant, they help you find relevant articles, analyze information, and even improve your writing!

Imagine being able to find hundreds of relevant research papers in minutes,  or getting a clear summary of a complex article with the click of a button. That's the magic of AI research assistants.

Some specialize in specific areas, like grammar and plagiarism checking, while others focus on broader tasks like literature review and research question development.  

No matter your research needs, there's an AI tool out there to help you save time, improve your work, and produce higher-quality research. 

Let's look closer at the features that a research AI tool offers 

These AI-powered tools offer a variety of features such as:

• Effortless searching: Quickly find high-quality research papers by entering your topic.
• Smarter literature reviews: Get suggestions for key studies, authors, and research trends.
• Enhanced writing: Improve your writing with grammar checks, stylistic suggestions, and help with complex concepts.
• Citation management: Easily manage and format your citations to avoid plagiarism.
• Research organization: Build your research library and organize articles for easy access.

These are just a few examples of how AI research tools can save you time and effort, allowing you to focus on the analysis and critical thinking that truly matters. 

Some tools even go beyond and offer a complete suite of AI features that cut down more than half of the research time.

Research can be a time-consuming endeavour. Sifting through mountains of literature, analyzing data, and crafting clear arguments can feel overwhelming. However, you can streamline much of this research process with Artificial Intelligence (AI) tools like Research AI tools. 

Here are some benefits you can gain with Research AI tools:

Effortless Information Retrieval: AI tools can search vast databases in seconds, pinpointing relevant studies and data tailored to your specific research question.

Smarter Literature Reviews: No more wading through mountains of papers. AI can recommend key research articles, and influential authors, and highlight emerging trends within your field, saving you time and ensuring a comprehensive review.

Idea Generation: If you struggle to spark new research ideas, then AI can help you. It can brainstorm fresh research questions, and hypotheses, and even suggest innovative experiment designs to propel your research forward.

Writing Assistant & Editor:  You can improve your writing and streamline your workflow with AI's editing prowess. Get real-time grammar and punctuation checks , stylistic suggestions, and clear explanations of complex concepts, all designed to elevate the quality of your research writing.

Enhanced Efficiency: AI automates tedious tasks like citation management and formatting, freeing you to focus on the analysis and interpretation of your research findings.

Personalized Research Assistant: AI tools can adapt to your research interests, suggesting relevant articles, recommending new avenues for exploration, and even summarizing complex research papers for a clearer understanding.

There are different AI tools present on the internet for different needs. So with the vast array of AI-powered research assistants available, selecting the most suitable tool can be problematic. 

Here are some key factors to consider, when you choosing the best AI Tools for Research:

Your Research Needs: Identify your specific needs. Are you searching for literature, summarizing complex papers, or improving your writing? Different tools excel in various areas.

Features Offered: Align the tool's features with your needs. Do you require real-time citation suggestions or plagiarism checkers?

Data Accuracy and Credibility: Ensure the tool retrieves information from reliable sources. Scite.ai stands out for highlighting the credibility of research claims.

Ease of Use: Consider the platform's user-friendliness. Look for intuitive interfaces and clear instructions.

Cost: AI tools often have varying pricing structures. Some offer free trials or basic plans, while others require subscriptions. Determine your budget and choose a tool that aligns with it.

Integration Capabilities: Does the tool integrate with your existing workflow? Look for options that seamlessly connect with your preferred reference managers or writing platforms.

Most importantly, remember that AI research assistants are only there to increase your productivity in the research process, not to replace it .

1. Elephas  

Elephas is an innovative AI tool designed to supercharge your research and writing efficiency. It utilizes advanced technology to break down complex research papers, YouTube videos, and other content, extracting the key points and saving you valuable time.

Additionally, Elephas goes beyond summarizing – it can seamlessly integrate with your workflow and rewrite content in various tones, making it a versatile companion for all your writing needs. 

Elephas doesn't just summarize research papers; it extracts key points and integrates seamlessly with your workflow. Whether you're a student, researcher, or content creator, Elephas helps you achieve more in less time.

Effortless Sum marization: Extract key points from research papers and YouTube videos with ease.

Centralized Hub: Keep all your research summaries organized in one place with Elephas Super Brain .

Seamless Content Creation: Create professional emails, engaging social media posts, and documents in just a few clicks.

Multiple Rewrite Modes: Choose from a variety of writing styles to make your content more engaging.

Super-Command Bar: Increase your productivity with features like article summarization and data extraction.

Elephas is also one of the best AI Tools for Summarizing Research Papers in the market right now. And it bundles up with a powerful iOS app as well.

It works locally and it's 100% privacy friendly!

If you own a Mac, you should definitely try it out.

ChatGPT , the tool behind the existence of many AI tools, is undeniably one of the best AI tools for research. With the right prompts, you can easily summarize any news articles , long notes, etc., in seconds. You can also ask ChatGPT research-related questions to gain a better understanding of research papers. Furthermore, you can improve your writing and avoid any grammar and punctuation mistakes. With the help of ChatGPT, the number of things you can do is endless.

Effortless Information Retrieval: Find the studies and data you need in a flash.

Smarter Literature Reviews: Get suggestions for key papers, authors, and research trends.

Idea Generation on Demand: Spark new research questions, hypotheses, and experiment designs.

Writing Assistant: Improve your writing with grammar checks, stylistic suggestions, and simplified explanations of complex concepts.

• Premium Plan Starts at $20/month 

Some users have reported false money deductions and low-quality service provided in the premium subscription.

3. Typeset.io

Typeset.io streamlines the entire academic writing process, saving you time and frustration.  This user-friendly platform offers a variety of features to help you write, collaborate, and publish top-notch research. From predefined templates to AI-powered writing assistance, Typeset.io empowers researchers of all levels to achieve their scholarly goals.

Effortless Formatting: Predefined templates ensure your paper meets journal requirements.

Citation Breeze: Manage citations and references effortlessly, with automatic generation.

Seamless Collaboration: Work together on research papers in real time.

Smart Journal Selection: Find the perfect fit for your research with a built-in journal database.

Premium Plan Starts at $7.78/month

Users have reported that the tool doesn't notify at the end of the free trial and sneakily charges for the premium plan. Additionally, once the plan is purchased, the money is non-refundable. Some have claimed that even after cancelling the subscription, the customer service did not cancel it and still charged their cards.

4. Quillbot 

Quillbot is your AI research companion, offering several time-saving features to streamline your workflow. It is designed to assist researchers of all levels. This tool utilizes advanced learning algorithms to enhance your writing and comprehension skills. With Quillbot, you can confidently paraphrase text, summarize complex materials, and ensure clear, plagiarism-free writing. Additionally, you can perform citations with high accuracy. Quillbot streamlines your workflow and strengthens your writing.

Paraphrasing & Summarizing: Quillbot rewrites sentences and condenses lengthy passages, saving you time and effort.

Language Enhancement & Learning: Improve your writing with advanced suggestions and explanations, perfect for non-native speakers.

Research Brainstorming: Generate fresh ideas from just a few keywords, overcoming writer's block.

Academic Accuracy & Citation Help: Ensure your writing matches specific citation styles and uses precise academic language.

• Premium Plan starts at $4.17/month 

Users have reported that the tool is working slowly when used in Microsoft Word, and it often uses complex words while paraphrasing. Some have also reported that the rephrased content on Quillbot is detected as AI-generated content on various AI detection tools.

5. Wordvice.ai

Wordvice AI is one of the best AI tools for research, it is your one-stop shop for powerful writing assistance. This AI-powered tool uses cutting-edge technology to streamline your research workflow, saving you time and effort. From basic grammar and clarity checks to advanced plagiarism detection, Wordvice AI helps you to write with confidence and produce polished, original academic content.

All-in-one editing: Grammar, style, clarity, and fluency checks with real-time feedback.

Vocabulary booster: Get suggestions for synonyms and alternative phrasing to diversify your writing.

Academic writing companion: Ensures proper citation format, maintains a scholarly tone, and adheres to research conventions.

Originality assured: Scans millions of sources to prevent plagiarism in your work.

Premium Plan starts at $9.95/month 

Users have reported that certain sentence patterns generated by AI are already found on existing web pages, which has led to an increase in plagiarism within content.

6. Consensus AI

Consensus AI is an innovative platform that uses artificial intelligence to simplify your search process. In just minutes, Consensus AI can search through vast databases and deliver hundreds of relevant, high-quality research papers directly to you. Also, Consensus AI filters results by date, study type, and journal quality, ensuring you find high-quality, credible sources to strengthen your research.

AI-powered Search Engine: Enter your research question and let Consensus AI scour vast databases to find relevant papers.

Time-Saving Efficiency: Gather hundreds of papers in minutes, freeing you up to focus on analysis and writing.

Comprehensive Results: Access a diverse range of studies, including randomized trials, reviews, and observational studies.

High-Quality Papers: Filter results by journal quality to ensure the credibility of your sources.

• Premium Plan Starts at $8.99/month 

Users have reported that when we try to share the live demo over Zoom, the tool becomes slow and hangs. They think it is a hassle to jump between the browser and Zoom. They suggest introducing some integration features in the tool as a good solution.

7. Scite.ai 

Scite.ai is one of the best for reliable research assistance powered by Artificial Intelligence.  Scite.ai tackles a common problem with AI research tools – unreliable citations.  Unlike others, Scite.ai provides you with real citations to published papers,  so you can be confident in the information you use. Even better, Scite.ai can analyze the research and tell you how many studies support or challenge a specific claim. 

Create Dashboards: Organize your research findings in a user-friendly format.

Journal and Institution Metrics: Gain insights into the reputation of academic sources.

Interactive Visualizations: You can see research trends and connections come through visualizations of the tool. 

Measure Claim Credibility: Scite.ai analyzes the strength of a claim by showing you how many studies support or refute it.

Premium Plan starts at $20/month 

Users have noticed that sometimes the tool produces inaccurate citations, which can be problematic for researchers who rely on its accuracy. Additionally, some users believe that the tool's pricing is significantly higher compared to its competitors.

8. Scholarcy

Scholarcy is an AI-powered tool that acts like a personal research assistant, summarizing complex articles, reports, and even book chapters for you.  Scholarcy quickly helps you understand the key points of any document and assess its relevance to your work, saving you precious time and effort. Whether you're a researcher, student, or just curious about the latest advancements, Scholarcy helps you quickly grasp key findings and identify relevant sources

Key Points at a Glance: Scholarcy extracts crucial information and organizes it into clear categories, making it easy to grasp the main ideas.

Seamless Integration: Scholarcy offers handy Chrome and Edge browser extensions, allowing you to summarize research directly from your web browser.

Visual Aids: Scholarcy can extract figures, tables, and images from articles, providing a more comprehensive understanding of the research.

Organized Knowledge: Build your searchable database of summarized research, making it easy to revisit key information later.

• Premium Plan Starts at $4.99/month 

Some users are not satisfied with the complete summaries produced by Scholarcy, as some of the sentences are not actual sentences and need to be corrected. Additionally, some sentences do not make any sense. Other users have claimed that the quality of the tool has significantly dropped in recent months and it feels glitchy while using it.

9. ProofHub

ProofHub is one of the best AI tools for research to streamline research projects. It's an all-in-one project management tool designed specifically to make research teams more efficient and effective. ProofHub centralizes everything your team needs in a single platform, allowing seamless collaboration and communication.  Save valuable time and avoid confusion by ditching the scattered emails, documents, and endless meetings.

Effortless Task & Project Management: Organize your research projects with ease using powerful tools like Kanban boards and Gantt charts.

Centralized Hub for Collaboration: Keep your team on the same page with a central platform for file sharing, discussions, and real-time feedback.

Streamlined Time Tracking & Scheduling: Never miss a deadline again! ProofHub's time tracking and scheduling features help you stay on top of your research project's progress.

Automated Workflows: Save even more time by automating repetitive tasks and creating custom workflows perfectly suited to your research needs.

• Premium Plan Starts at $45/month 

Users have expressed dissatisfaction with the user interface and email notifications of the tool, stating that they are not up to par. In addition, some have reported that certain features in Proofhub are not as impressive as those of its competitors.

10. Research Rabbit

ResearchRabbit is another best AI tools for research, it helps you navigate through the vast world of scientific literature. Nicknamed the "Spotify for Papers," this innovative tool lets you explore research like never before. Build collections of articles you find interesting, and ResearchRabbit will cleverly suggest new papers that align with your specific interests. No more endless searches – ResearchRabbit becomes your personalized research assistant, saving you time and frustration.

Build your research library: Collect and organize articles you find interesting, all in one place.

Smart recommendations: Never miss a groundbreaking study! ResearchRabbit suggests new papers based on your interests, saving you valuable time.

Visualize connections: See how different research areas, authors, and ideas are linked together.

Collaboration made easy: Share your research collections with colleagues to work together more effectively.

Free Forever 

We couldn't find any public reviews for the Research Rabbit. Therefore, we advise users to proceed with caution.

Many best AI tools for research suit different types of people, and these research AI tools have streamlined tasks and uncovered connections. However, they still have many limitations compared to manual research processes. Here's a closer look.

1. Accuracy and Bias: AI tools rely on the data they're trained on. If the data is biased or inaccurate, the results can be misleading. It's crucial to critically evaluate AI outputs and not rely solely on them.

2. Depth vs. Breadth: AI tools can efficiently scan vast amounts of literature, but they may miss nuances or subtleties within research papers. In-depth analysis and critical thinking remain essential for a comprehensive understanding.

3. Overreliance on Automation: AI shouldn't replace the core research process. Researchers should use AI to streamline tasks, not eliminate critical steps like evaluating source credibility and understanding research context.

4. Black Box Problem:  Sometimes, AI won't explain its reasoning behind results. This lack of transparency can make it difficult to assess the trustworthiness of findings or suggestions.

5. Limited Scope: AI tools might not cover all relevant sources, especially niche or emerging research areas. Supplement your search with traditional methods like library databases and expert consultations.

In our community, we have found Elephas being used by some professors at a university, and they have shared their experiences on how they used it in their lesson research process. Here is how they did it:

1. Summarization: The professor utilized Elephas' ability to generate concise summaries of different textbooks and research papers. This allowed him to quickly grasp the core arguments and findings of numerous studies, saving him hours of dedicated reading time.

2. Video Research: Then the professor had to gather more knowledge to create a lesson plan, so he searched for some of the best lengthy video lectures. Packed with historical insights, these videos were no longer a trouble because Elephas efficiently summarized key points from them, enabling our professor to include this valuable information in his lessons without spending hours glued to the screen.

3. Building Knowledge Base: Finally, the professor used Elephas Super Brain to create a centralized hub for all his research summaries. This eliminated the need to sift through countless folders and documents, allowing him to access critical information instantly. Additionally, he utilized the Super Brain to better understand the lesson plan through the Super Brain chat feature of Elephas.

Let's see what Elephas was able to do for our professor who is striving to teach his students in-depth subject knowledge:

1. Increased Efficiency: The professor has seen a significant reduction in research time, freeing up valuable hours for lesson planning and development.

2. Deeper Lesson Understanding: With more time at his disposal, our professor was able to delve into the research he found most compelling, leading to a deeper understanding of historical topics.

3. Engaging Lectures: By using key insights from research summaries provided by Elephas, the professor's lectures became more informative and engaging for his students, helping in their understanding of the topic faster than before.

The professor's experience explains how Elephas can revolutionize the research process for academics. By saving time and streamlining workflows, Elephas helps researchers get deeper into their respective fields and create truly impactful learning experiences and also cut their research process to more than half.

Conclusion  

In summary, AI research assistants are transforming how researchers approach their work. These tools can summarize complex information, find relevant studies, and even suggest new research ideas. Top choices include Elephas (which summarizes research papers and YouTube videos), ChatGPT (which summarizes articles and answers questions), and Typeset.io (which streamlines academic writing).

However, make sure to pick the best AI tool for research based on your requirements. Also, remember that while AI offers significant time savings and improved efficiency, it shouldn't replace critical thinking and human expertise in research because AI has several limitations that can degrade your research quality.

Elephas is the best AI tool for research, offering key features for researchers such as summarizing research papers, articles, and YouTube videos. Additionally, you can upload data to a "super brain" for retrieval and chat with uploaded PDFs for deeper understanding. This makes Elephas a strong AI tool for research tasks

Yes, ChatGPT can be a helpful tool for initial research exploration. It can brainstorm ideas, summarize complex topics, and even find relevant sources. However, for in-depth research, specialized academic databases and citation tools are better suited. These resources provide more reliable and accurate information, often with features like peer-reviewed content and advanced search options.

AI is revolutionizing research by summarizing complex information and assisting with content creation. AI tools can analyze research papers, articles, and even videos to extract key findings, saving researchers time and effort. AI can also rewrite content in different tones, making it a valuable asset for researchers who need to communicate their findings to various audiences.

Elephas is an AI tool designed to boost research and writing efficiency for PhD students and researchers. It summarizes complex research papers, YouTube videos, and other content, saving you time. Elephas also integrates with your workflow and rewrites content in various tones, making it a versatile PhD buddy.

Mac Productivity

AI assistant

Personal Knowledge Management

Don't miss out

Get 1 AI productivity tip delivered to your inbox every week. For FREE!

Elephas helps you write faster and smarter on Mac - It's the best AI powered writing assistant for your Apple devices - Mac, iPhone and iPad.

You may also want to read

Top 10 Best Browsers for Mac in 2024 (Free + Paid)

Pinned Post

10 Things We Can Expect from Apple 2024 WWDC Event

How to Write a Research Paper Using AI? (2024) | Best Tips and Tools

Previous Post

Linked research data from idea to impact

Accelerate research discovery, we make finding and interpreting global research data fast and simple..

Dimensions provides a suite of research products and time-saving solutions that connect the dots across the research ecosystem.

You can be confident that you’re not missing anything vital, as we host the largest collection of interconnected global research data and layer it with visual applications to fuel discovery.

Whatever you need to uncover, our platform and solutions can drive your decision-making and propel information discovery, saving you hours of time.

Dimensions Analytics

Find the information you need in millions of publications, patents, datasets, grants, and more, and get an overview of topics, organizations, people, or network profiles.

Dimensions Landscape & Discovery

Horizon scan in seconds, with your own customized landscape analysis dashboard and visually explore publications, grants, patents, and clinical trials within minutes.

Dimensions Perspectives & Insights

Get insights to support research strategy, impact assessment and collaboration analysis. Benchmark against others to identify trends, patterns and opportunities.

Dimensions Expert Identifier

Quickly identify experts with an extensive list of researchers precisely matched to your business, featuring additional analytical information not found anywhere else.

Dimensions Reviewer Finder

Find expert reviewers fast – as you pinpoint reviewers for grant applications or publication manuscripts

Dimensions Research Security

Identify potential risks to your research security, verify disclosures, and review research networks – quickly, efficiently, and thoroughly

Dimensions GBQ

Seamlessly combine Dimensions data with your own private and external datasets to analyze billions of data points in seconds and create actionable insights.

Dimensions API

Stream research data into your workflows without manual intervention and access full text search and data retrieval for use in complex analyses and visualizations

“PLOS relies on Dimensions for baseline data about institutions and their funding sources for agreement discussions but also for internal business analytics”

SARA ROUHI, PLOS

“With Dimensions, I don’t waste my time clicking through and switching between databases to find the answers to my questions.”

AIDAN MORRISON, EMERALD PUBLISHING

“Dimensions is becoming a popular resource across campus and earns high marks for its ease-of-use.”

Donna Axel, University of Colorado

“Dimensions Analytics has a wider coverage than other databases in the space”.

Aruna Rajan, Illumina

“Dimensions has improved the ability of the National Physical Laboratory to do research evaluation and analysis by a factor of 10”

Jenny Wooldridge, National Physical Laboratory

Dimensions webinars

Powering research discovery and interpretation with ai.

Watch our on demand webinar to find out more about Dimension’s commitment to advancing research and science, and support Open Research initiatives through AI technology. We will present our latest features and products that use AI to make research discove…

New and Notable Updates for Scholarly Publishers

Discover what’s new and notable for publishers in this on demand webinar. In the session, Tyler Ruse, Director of Publisher Solutions, and Michelle Herbert, Product Engagement Specialist, walk you through exciting new updates and features from Dimensions.

Elevating SDG Impact: Insights, Trends, and Automations for Publishers

Scholarly publishers play a crucial role in advancing the United Nations’ Sustainable Development Goals (SDGs), by disseminating knowledge, fostering collaboration, and promoting responsible publishing practices.  The SDG Publishers Compact, signed b…

Featured content

Article uncovers extensive use of chatbots in scientific publications.

A recent Scientific American article highlights how rampant the practice is by analyzing the publication data obtained from databases such as Dimensions.

Inform open access publishing strategies and evaluate transformative agreements

How to find and analyze data surrounding authorship and funding in topical areas by country, geography, institution, and funder.

A new approach to prospecting and market mapping

Learn how a commercial team uses Dimensions to drive business growth with prospecting and market mapping.

Sign up for our newsletter

Ask a question, get an answer backed by real research

1.2b citation statements extracted and analyzed

187 m articles, book chapters, preprints, and datasets.

Trusted by leading Universities, Publishers, and Corporations across the world.

Read what research articles say about each other

scite is an award-winning platform for discovering and evaluating scientific articles via Smart Citations. Smart Citations allow users to see how a publication has been cited by providing the context of the citation and a classification describing whether it provides supporting or contrasting evidence for the cited claim.

Extracted citations in a report page

Never waste time looking for and evaluating research again.

Our innovative index of Smart Citations powers new features built to make research intuitive and trustworthy for anyone engaging with research.

Search Citation Statements

Find information by searching across a mix of metadata (like titles & abstracts) as well as Citation Statements we indexed from the full-text of research articles.

Create Custom Dashboards

Build and manage collections of articles of interest -- from a manual list, systematic review, or a search -- and get aggregate insights, notifications, and more.

Reference Check

Evaluate how references from your manuscript were used by you or your co-authors to ensure you properly cite high quality references.

Journal Metrics

Explore pre-built journal dashboards to find their publications, top authors, compare yearly scite Index rankings in subject areas, and more.

Large Language Model (LLM) Experience for Researchers

Assistant by scite gives you the power of large language models backed by our unique database of Smart Citations to minimize the risk of hallucinations and improve the quality of information and real references.

Use it to get ideas for search strategies, build reference lists for a new topic you're exploring, get help writing marketing and blog posts, and more.

Assistant is built with observability in mind to help you make more informed decisions about AI generated content.

Here are a few examples to try:

"How many rats live in NYC?"

"How does the structure of a protein affect its function?"

Awards & Press

Trusted by researchers and organizations around the world

Over 969,000 students, researchers, and industry experts use scite

See what they're saying

scite is an incredibly clever tool. The feature that classifies papers on whether they find supporting or contrasting evidence for a particular publication saves so much time. It has become indispensable to me when writing papers and finding related work to cite and read.

Emir Efendić, Ph.D

Maastricht University

As a PhD student, I'm so glad that this exists for my literature searches and papers. Being able to assess what is disputed or affirmed in the literature is how the scientific process is supposed to work, and scite helps me do this more efficiently.

Kathleen C McCormick, Ph.D Student

scite is such an awesome tool! It’s never been easier to place a scientific paper in the context of the wider literature.

Mark Mikkelsen, Ph.D

The Johns Hopkins University School of Medicine

This is a really cool tool. I just tried it out on a paper we wrote on flu/pneumococcal seasonality... really interesting to see the results were affirmed by other studies. I had no idea.

David N. Fisman, Ph.D

University of Toronto

Do better research

Join scite to be a part of a community dedicated to making science more reliable.

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

[email protected]

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Copyright © 2024 scite LLC. All rights reserved.

Made with 💙 for researchers

Part of the Research Solutions Family.

Verifying that you are not a robot...

Reference management. Clean and simple.

The top list of academic search engines

1. Google Scholar

4. science.gov, 5. semantic scholar, 6. baidu scholar, get the most out of academic search engines, frequently asked questions about academic search engines, related articles.

Academic search engines have become the number one resource to turn to in order to find research papers and other scholarly sources. While classic academic databases like Web of Science and Scopus are locked behind paywalls, Google Scholar and others can be accessed free of charge. In order to help you get your research done fast, we have compiled the top list of free academic search engines.

Google Scholar is the clear number one when it comes to academic search engines. It's the power of Google searches applied to research papers and patents. It not only lets you find research papers for all academic disciplines for free but also often provides links to full-text PDF files.

• Coverage: approx. 200 million articles
• Abstracts: only a snippet of the abstract is available
• Related articles: ✔
• References: ✔
• Cited by: ✔
• Links to full text: ✔
• Export formats: APA, MLA, Chicago, Harvard, Vancouver, RIS, BibTeX

BASE is hosted at Bielefeld University in Germany. That is also where its name stems from (Bielefeld Academic Search Engine).

• Coverage: approx. 136 million articles (contains duplicates)
• Abstracts: ✔
• Related articles: ✘
• References: ✘
• Cited by: ✘
• Export formats: RIS, BibTeX

CORE is an academic search engine dedicated to open-access research papers. For each search result, a link to the full-text PDF or full-text web page is provided.

• Coverage: approx. 136 million articles
• Links to full text: ✔ (all articles in CORE are open access)
• Export formats: BibTeX

Science.gov is a fantastic resource as it bundles and offers free access to search results from more than 15 U.S. federal agencies. There is no need anymore to query all those resources separately!

• Coverage: approx. 200 million articles and reports
• Links to full text: ✔ (available for some databases)
• Export formats: APA, MLA, RIS, BibTeX (available for some databases)

Semantic Scholar is the new kid on the block. Its mission is to provide more relevant and impactful search results using AI-powered algorithms that find hidden connections and links between research topics.

• Coverage: approx. 40 million articles
• Export formats: APA, MLA, Chicago, BibTeX

Although Baidu Scholar's interface is in Chinese, its index contains research papers in English as well as Chinese.

• Coverage: no detailed statistics available, approx. 100 million articles
• Abstracts: only snippets of the abstract are available
• Export formats: APA, MLA, RIS, BibTeX

RefSeek searches more than one billion documents from academic and organizational websites. Its clean interface makes it especially easy to use for students and new researchers.

• Coverage: no detailed statistics available, approx. 1 billion documents
• Abstracts: only snippets of the article are available
• Export formats: not available

Consider using a reference manager like Paperpile to save, organize, and cite your references. Paperpile integrates with Google Scholar and many popular databases, so you can save references and PDFs directly to your library using the Paperpile buttons:

Google Scholar is an academic search engine, and it is the clear number one when it comes to academic search engines. It's the power of Google searches applied to research papers and patents. It not only let's you find research papers for all academic disciplines for free, but also often provides links to full text PDF file.

Semantic Scholar is a free, AI-powered research tool for scientific literature developed at the Allen Institute for AI. Sematic Scholar was publicly released in 2015 and uses advances in natural language processing to provide summaries for scholarly papers.

BASE , as its name suggest is an academic search engine. It is hosted at Bielefeld University in Germany and that's where it name stems from (Bielefeld Academic Search Engine).

CORE is an academic search engine dedicated to open access research papers. For each search result a link to the full text PDF or full text web page is provided.

Science.gov is a fantastic resource as it bundles and offers free access to search results from more than 15 U.S. federal agencies. There is no need any more to query all those resources separately!

Unlock Your Research Potential with Jenni AI

Are you an academic researcher seeking assistance in your quest to create remarkable research and scientific papers? Jenni AI is here to empower you, not by doing the work for you, but by enhancing your research process and efficiency. Explore how Jenni AI can elevate your academic writing experience and accelerate your journey toward academic excellence.

Loved by over 1 million academics

Academia's Trusted Companion

Join our academic community and elevate your research journey alongside fellow scholars with Jenni AI.

Effortlessly Ignite Your Research Ideas

Unlock your potential with these standout features

Boost Productivity

Save time and effort with AI assistance, allowing you to focus on critical aspects of your research. Craft well-structured, scholarly papers with ease, backed by AI-driven recommendations and real-time feedback.

Get started

Overcome Writer's Block

Get inspiration and generate ideas to break through the barriers of writer's block. Jenni AI generates research prompts tailored to your subject, sparking your creativity and guiding your research.

Unlock Your Full Writing Potential

Jenni AI is designed to boost your academic writing capabilities, not as a shortcut, but as a tool to help you overcome writer's block and enhance your research papers' quality.

 Ensure Accuracy

Properly format citations and references, ensuring your work meets academic standards. Jenni AI offers accurate and hassle-free citation assistance, including APA, MLA, and Chicago styles.

Our Commitment: Academic Honesty

Jenni AI is committed to upholding academic integrity. Our tool is designed to assist, not replace, your effort in research and writing. We strongly discourage any unethical use. We're dedicated to helping you excel in a responsible and ethical manner.

How it Works

Sign up for free.

To get started, sign up for a free account on Jenni AI's platform.

Prompt Generation

Input your research topic, and Jenni AI generates comprehensive prompts to kickstart your paper.

Research Assistance

Find credible sources, articles, and relevant data with ease through our powerful AI-driven research assistant.

Writing Support

Draft and refine your paper with real-time suggestions for structure, content, and clarity.

Citation & References

Let Jenni AI handle your citations and references in multiple styles, saving you valuable time.

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

How much does jenni ai cost, how can jenni ai assist me in writing complex academic papers, can jenni ai handle different types of academic papers, such as essays, research papers, and dissertationss jenni ai maintain the originality of my work, how does artificial intelligence enhance my academic writing with jenni ai.

Can Jenni AI help me structure and write a comprehensive literature review?

Will using Jenni AI improve my overall writing skills?

Can Jenni AI assist with crafting a thesis statement?

What sets Jenni AI apart as an AI-powered writing tool?

Can I trust Jenni AI to help me maintain academic integrity in my work?

Choosing the Right Academic Writing Companion

Get ready to make an informed decision and uncover the key reasons why Jenni AI is your ultimate tool for academic excellence.

Feature Featire

COMPETITORS

Enhanced Writing Style

Jenni AI excels in refining your writing style and enhancing sentence structure to meet academic standards with precision.

Competitors may offer basic grammar checking but often fall short in fine-tuning the nuances of writing style.

Academic Writing Process

Jenni AI streamlines the academic writing process, offering real-time assistance in content generation and thorough proofreading.

Competitors may not provide the same level of support, leaving users to navigate the intricacies of academic writing on their own.

Scientific Writing

Jenni AI is tailored for scientific writing, ensuring the clarity and precision needed in research articles and reports.

Competitors may offer generic writing tools that lack the specialized features required for scientific writing.

Original Content and Academic Integrity

Jenni AI's AI algorithms focus on producing original content while preventing plagiarism, ensuring academic integrity.

Competitors may not provide robust plagiarism checks, potentially compromising academic integrity.

Valuable Tool for Technical Writing

Jenni AI extends its versatility to technical writing, aiding in the creation of clear and concise technical documents.

Some competitors may not be as well-suited for technical writing projects.

User-Friendly Interface

Jenni AI offers an intuitive and user-friendly interface, making it easy for both novice and experienced writers to utilize its features effectively.

Some competitors may have steeper learning curves or complex interfaces, which can be time-consuming and frustrating for users.

Seamless Citation Management

Jenni AI simplifies the citation management process, offering suggestions and templates for various citation styles.

Competitors may not provide the same level of support for correct and consistent citations.

Ready to Revolutionize Your Research Writing?

Sign up for a free Jenni AI account today. Unlock your research potential and experience the difference for yourself. Your journey to academic excellence starts here.

• Do Not Sell My Personal Info

•  ⋅ 

Google AI Overviews: New Research Offers Insights

New research by BrightEdge offers insights into what kinds of search queries are triggering AI Overviews across multiple verticals

New research by BrightEdge offers a snapshot of the kinds of queries that tend to show Google AI Overviews (AIO) and provides insights into the kinds of queries and verticals where AIO are more prevalent.

The findings show dramatic differences in the amount of AI Overviews shown across different verticals in a way that reflects the kinds of queries that are common. This effect works in reverse as well, where some verticals experience less AIO search features.

Is This A Paradigm Shift?

While BrightEdge calls it the greatest paradigm shift in decades, I think that’s understating shifts to Google search in the recent past, not just the ones in 2024. Something that’s not widely understood is that Google Search has been an AI Search engine since at least 2015 with the introduction of RankBrain and other subsequent changes to the backend side of search.

The big change in Search this year is that AI is more obvious on the front-end as a Feature in Search, largely replacing the role that Featured Snippets once played. Perhaps more importantly there may have been an infrastructure change at the beginning of 2024.

BrightEdge Generative Parser

BrightEdge has a technology, called the Generative Parser, which tracks and analyzes patterns in Google’s AI search features. BrightEdge used their Generative Parser to produce research findings about Google’s new AI Overviews (AIO) search feature.

Albert Gouyet, VP of Operations at BrightEdge said this about the BrightEdge Generative Parser:

“It’s fascinating to see the BrightEdge Generative Parser™ giving marketers a front-row seat into how AI in search is developing and giving the community a glimpse into the future. For marketers who rely on organic traffic, early indications suggest that AI will help reach new customers and present new opportunities to create content that serves multiple needs and elevates brand performance.”

What Triggers AIO

BrightEdge’s report indicates that Featured Snippets and questions were likely to trigger the AIO feature. Featured Snippets are answers to questions that are created with direct quotes from websites. BrightEdge found that AI Overviews were more likely to appear when there was also a Featured Snippet.

What Doesn’t Trigger AI Overviews

The research showed that local search queries were the least likeliest to trigger an AI Overview search result. That makes sense because a user is looking for a structured search result (business names, addresses, phone numbers), information that can’t be usefully summarized.

Similarly, search queries that generate sitelinks were also less likely to trigger AIO. Sitelinks are search results related to branded searches which feature multiple links to inner pages of a website. For example, searching for the name of a clothing store can generate a search result that features inner pages for women’s clothes, men’s clothes, etc. This also makes sense because it’s the kind of search query that is best answered with direct data and not a summary.

Verticals Most Likely To Contain AIO

Search results that tended to feature AI Overviews were wildly different when compared by verticals (verticals means specific industries or topics). This likely doesn’t mean that Google was targeting specific verticals for showing more AIO. Search features are always tied to the helpfulness of the features. The helpfulness of features are tested with the Search Quality Raters , workers who test out new kinds of search results and rate them for helpfulness and other criteria.

Search queries related to Healthcare tended to generate AI Overviews at a rate of 63% of the time. That makes sense for search queries that are information-seeking.

B2B technology queries tended to generate AIO results 32% of the time while Ecommerce search queries triggered AI Overviews 23% of the time.

Interestingly, restaurants and travel related queries did not tend to trigger AIO results.

AIO Shown Less Often Than SGE

Another interesting data point is that AIO is triggered 20% less times than Search Generative Experience (SGE) answers were.

BrightEdge offered three insights related to why AIO is shown less than the experimental SGE was.

“This indicates that AI is getting more precise when generating helpful experiences. This is likely because AI now caters better to people’s needs, such as looking for summaries, recommendations, or conversational experiences. Ultimately, Google is getting better at selecting answers.”

BrightEdge research pointed out that Google is improving the ability to anticipate follow up questions by providing AI search summaries that more completely answer a question.

They write:

“Since Google l/O, the overlap between citations in AI and traditional results has diminished. Google is ensuring users do not get the same results in the two types of different results. It is also now delivering on its promise to do the second, third, and fourth search for you. AI is beginning to anticipate the following question and give options before a user even asks. This often happens with ‘what,’ ‘where,’ and ‘how’ intent-based queries.”

Early Days Of AIO

Google has received overwhelmingly negative reviews from users and the news media about the quality of Google’s AI Overviews, which in turn can lead to trust issues. BrightEdge’s report can be considered a snapshot of Google AIO today and I’m certain BrightEdge will be back with new data in the future when Google’s (AI) SERPs eventually change again.

Featured image by Shutterstock/Marco Lazzarini

I have 25 years hands-on experience in SEO and have kept on  top of the evolution of search every step ...

Subscribe To Our Newsletter.

Conquer your day with daily search marketing news.

To revisit this article, visit My Profile, then View saved stories .

• Backchannel
• Newsletters
• WIRED Insider
• WIRED Consulting

Reece Rogers

Google’s AI Overview Search Results Copied My Original Work

Last week, an AI Overview search result from Google used one of my WIRED articles in an unexpected way that makes me fearful for the future of journalism.

I was experimenting with AI Overviews, the company’s new generative AI feature designed to answer online queries. I asked it multiple questions about topics I’ve recently covered, so I wasn’t shocked to see my article linked, as a footnote, way at the bottom of the box containing the answer to my query. But I was caught off guard by how much the first paragraph of an AI Overview pulled directly from my writing.

The following screenshot on the left is from an interview I conducted with one of Anthropic’s product developers about tips for using the company’s Claude chatbot . The screenshot on the right is a portion of Google’s AI Overview that answered a question about using Anthropic’s chatbot. Reading the two paragraphs side by side, it feels reminiscent of a classroom cheater who copied an answer from my homework and barely even bothered to switch up the phrasing.

Without the AI Overviews enabled, my article was often the featured snippet highlighted at the top of Google search results, offering a clear link for curious users to click on when they were looking for advice about using the Claude chatbot. During my initial tests of Google’s new search experience , the featured snippet with the article still appeared for relevant queries, but it was pushed beneath the AI Overview answer that pulled from my reporting and inserted aspects of it into a 10-item bulleted list.

In email exchanges and a phone call, a Google spokesperson acknowledged that the AI-generated summaries may use portions of writing directly from web pages, but they defended AI Overviews as conspicuously referencing back to the original sources. Well, in my case, the first paragraph of the answer is not directly attributed to me. Instead, my original article was one of six footnotes hyperlinked near the bottom of the result. With source links located so far down, it’s hard to imagine any publisher receiving significant traffic in this situation.

“AI Overviews will conceptually match information that appears in top web results, including those linked in the overview,” wrote a Google spokesperson in a statement to WIRED. “This information is not a replacement for web content, but designed to help people get a sense of what's out there and click to learn more.” Looking at the word choice and overall structure of the AI Overview in question, I disagree with Google’s characterization that the result may be just a “conceptual match” of my writing. It goes further. Also, even if Google developers did not intend for this feature to be a replacement of the original work, AI Overviews provide direct answers to questions in a manner that buries attribution and reduces the incentive for users to click through to the source material.

“We see that links included in AI Overviews get more clicks than if the page had appeared as a traditional web listing for that query," said the Google spokesperson. No data to support this claim was offered to WIRED, so it's impossible to independently verify the impact of the AI feature on click-through rates. Also, it’s worth noting that the company compared AI Overview referral traffic to more traditional blue-link traffic from Google, not to articles chosen for a featured snippet, where the rates are likely much higher.

After I reached out to Google about the AI Overview result that pulled from my work, the experimental AI search result for this query stopped showing up, but Google still attempted to generate an answer above the featured snippet.

While many AI lawsuits remain unresolved, one legal expert I spoke with who specializes in copyright law was skeptical whether I could win any hypothetical litigation. “I think you would not have a strong case for copyright infringement,” says Janet Fries, an attorney at Faegre Drinker Biddle & Reath . “Copyright law, generally, is careful not to get in the way of useful things and helpful things.” Her perspective focused on the type of content in this specific example of original work, explaining that it is quite difficult to make a claim about instructional or fact-based writing, like my advice column, versus more creative work, like poetry.

I’m definitely not the first person to suggest focusing on your intended audience when writing chatbot prompts, so I agree that the fact-based aspect of my writing does complicate the overall situation. It’s hard for me, though, to imagine a world where Google arrives at that exact paragraph about Claude’s chatbot in its AI Overview results without referencing my work first.

By Joseph Cox

By Matt Burgess

By Dhruv Mehrotra

By Hannah Zeavin

Another copyright expert I spoke with was less certain about what would happen in court for a hypothetical copyright case based on my findings. “I still think we could put this in front of a jury,” says Kristelia García, a professor at Georgetown University Law Center . “And see if that jury would find it to be ‘substantially similar,’ which is the legal standard.”

To be clear, this is all hypothetical. I have no plans to bring litigation against Google. This reporting was done in the interest of informing the public about the impact of artificial intelligence and fostering useful discussion.

Whether or not Google infringed on WIRED’s copyright in this situation, I feel certain that if the company decides to expand the prevalence AI Overviews, then the feature will dramatically transform digital journalism, likely for the worse. Nilay Patel, cofounder and editor in chief at The Verge , often mentions the concept of “ Google Zero ,” or the day when publishers wake up and see that their tenuous traffic from the web’s largest referrer has fizzled out. Google’s dominant control over how people search the internet puts the company in a unique position to snuff out traffic, and potentially entire publications, by changing how its service functions .

With the journalism industry being already strapped for cash, it's easy to understand why corporate leaders at publications who are anxious about recent AI developments are rushing to sign licensing deals with major AI companies. The Associated Press , The Atlantic , the parent company of Business Insider and Politico, the Financial Times , Vox Media , the parent company of The Wall Street Journal, and digital publishing giant Dotdash Meredith all have contracts with OpenAI. Nevertheless, rank-and-file workers may not be thrilled about how their writing is sold off in these contracts.

The work of reliable journalists is clearly valuable to these AI-focused companies, even if they don’t pay to license the content from publishers. In a recent blog post from Liz Reid, Google’s head of search, she blamed user-generated content , specifically discussion forums, for why AI Overviews told one user to add nontoxic glue to pizza for extra cheese stickiness. The Reddit comment in question may have been from a user named “fucksmith.” By offering up direct, AI-summarized answers to user questions, Google places more onus on itself to get facts straight and highlight quality information.

And if you’re going to copy off someone’s homework, you'd better make sure it's a straight-A student’s paper—not some troll on Reddit.

You Might Also Like …

In your inbox: Will Knight's Fast Forward explores advances in AI

Welcome to the hellhole of programmatic advertising

How many EV charging stations does the US need to replace gas stations?

A nonprofit tried to fix tech culture —but lost control of its own

It's always sunny: Here are the best sunglasses for every adventure

Kate Knibbs

Lauren Goode

Will Knight

Steven Levy

Paresh Dave

The Four Ways Kayak Is Using AI

Justin Dawes , Skift

June 4th, 2024 at 7:04 PM EDT

Kayak is doing a lot of experiments with AI, not always in the most obvious ways.

Justin Dawes

Kayak has found multiple ways to use generative AI, and it’s not always how one may expect. 

Kayak chief scientist  Matthias Keller  discussed the metasearch engine’s recent AI projects on stage Tuesday at the Skift Data+AI Summit.

1. Productivity

Kayak is encouraging its employees to explore how generative AI helps them complete their work, Keller said.

“From the beginning, we made ChatGPT and other tools available to everyone, for everyone to find what works best for them.”

That could be as a translator or to help organize information, he said — but the point is that experimentation is happening, and it may lead to something more in the future.

“There is no single killer use-case yet, but it’s more like a lot of bread crumbs that are going to make a bread,” Keller said.

2. Integrations in ChatGPT and Copilot

Kayak was one of the first travel companies to develop a plugin for ChatGPT Plus, which allowed paid users to access specific flight information and links from Kayak. OpenAI discontinued the third-party plugin program in April and replaced it with GPTs , which are tailored versions of chatbots on ChatGPT — free for everyone as of last week.

Kayak has its own GPT, accessible under the Explore GPTS tab on the left panel of the ChatGPT homepage.

Kayak also has a connection with Microsoft Copilot. Bing search engine users can ask the Copilot chatbot for flight information and receive real-time information from Kayak.

3. Chatbot Tool

Keller also mentioned the new Ask Kayak tool, which is a reimagined travel search tool that the company is piloting.

Skift did a test of the product when it was released.

When it comes to trip planning, Ask Kayak doesn’t have real-time knowledge, only general information about travel destinations.

“And then you bring that together with our knowledge … and this then makes that that destination finder program based on generative AI.”

A primary use, as he highlighted, is that it helps the travelers ask for specific flights in simple language rather than having to sort through multiple filters.

“You may not want to work through these 20 different filters, and so now you can use the free text box,” he said.

4. Nonconventional Innovations

Kayak is also experimenting with consumer tools that aren’t a chatbot but still use generative AI to operate.

The company this year released a tool called PriceCheck. It can read flight fare information from a screenshot from another travel search platform, and then search for a better price.

Skift ran a test of the tool in March — and it seemed to work.

“It feels nothing like ChatGPT, but this is an innovation that would only be economic or doable — or basically buildable — with the help of generative AI.”

Have a confidential tip for Skift? Get in touch

Tags: artificial intelligence , booking holdings , kayak , online travel newsletter , SDAIS24 , skiftlive , the prompt , very online

Photo credit: Pictured: Matthias Keller of Kayak, left, in discussion with Skift executive editor Dennis Schaal.

Suggestions or feedback?

MIT News | Massachusetts Institute of Technology

• Machine learning
• Social justice
• Black holes
• Classes and programs

Departments

• Aeronautics and Astronautics
• Brain and Cognitive Sciences
• Architecture
• Political Science
• Mechanical Engineering

Centers, Labs, & Programs

• Abdul Latif Jameel Poverty Action Lab (J-PAL)
• Picower Institute for Learning and Memory
• Lincoln Laboratory
• School of Architecture + Planning
• School of Engineering
• School of Humanities, Arts, and Social Sciences
• Sloan School of Management
• School of Science
• MIT Schwarzman College of Computing

Controlled diffusion model can change material properties in images

Press contact :.

Previous image Next image

Researchers from the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) and Google Research may have just performed digital sorcery — in the form of a diffusion model that can change the material properties of objects in images. Dubbed Alchemist , the system allows users to alter four attributes of both real and AI-generated pictures: roughness, metallicity, albedo (an object’s initial base color), and transparency. As an image-to-image diffusion model, one can input any photo and then adjust each property within a continuous scale of -1 to 1 to create a new visual. These photo editing capabilities could potentially extend to improving the models in video games, expanding the capabilities of AI in visual effects, and enriching robotic training data.

The magic behind Alchemist starts with a denoising diffusion model: In practice, researchers used Stable Diffusion 1.5, which is a text-to-image model lauded for its photorealistic results and editing capabilities. Previous work built on the popular model to enable users to make higher-level changes, like swapping objects or altering the depth of images. In contrast, CSAIL and Google Research’s method applies this model to focus on low-level attributes, revising the finer details of an object’s material properties with a unique, slider-based interface that outperforms its counterparts. While prior diffusion systems could pull a proverbial rabbit out of a hat for an image, Alchemist could transform that same animal to look translucent. The system could also make a rubber duck appear metallic, remove the golden hue from a goldfish, and shine an old shoe. Programs like Photoshop have similar capabilities, but this model can change material properties in a more straightforward way. For instance, modifying the metallic look of a photo requires several steps in the widely used application.

“When you look at an image you’ve created, often the result is not exactly what you have in mind,” says Prafull Sharma, MIT PhD student in electrical engineering and computer science, CSAIL affiliate, and lead author on a new paper describing the work. “You want to control the picture while editing it, but the existing controls in image editors are not able to change the materials. With Alchemist, we capitalize on the photorealism of outputs from text-to-image models and tease out a slider control that allows us to modify a specific property after the initial picture is provided.”

Precise control

“Text-to-image generative models have empowered everyday users to generate images as effortlessly as writing a sentence. However, controlling these models can be challenging,” says Carnegie Mellon University Assistant Professor Jun-Yan Zhu, who was not involved in the paper. “While generating a vase is simple, synthesizing a vase with specific material properties such as transparency and roughness requires users to spend hours trying different text prompts and random seeds. This can be frustrating, especially for professional users who require precision in their work. Alchemist presents a practical solution to this challenge by enabling precise control over the materials of an input image while harnessing the data-driven priors of large-scale diffusion models, inspiring future works to seamlessly incorporate generative models into the existing interfaces of commonly used content creation software.”

Alchemist’s design capabilities could help tweak the appearance of different models in video games. Applying such a diffusion model in this domain could help creators speed up their design process, refining textures to fit the gameplay of a level. Moreover, Sharma and his team’s project could assist with altering graphic design elements, videos, and movie effects to enhance photorealism and achieve the desired material appearance with precision.

The method could also refine robotic training data for tasks like manipulation. By introducing the machines to more textures, they can better understand the diverse items they’ll grasp in the real world. Alchemist can even potentially help with image classification, analyzing where a neural network fails to recognize the material changes of an image.

Sharma and his team’s work exceeded similar models at faithfully editing only the requested object of interest. For example, when a user prompted different models to tweak a dolphin to max transparency, only Alchemist achieved this feat while leaving the ocean backdrop unedited. When the researchers trained comparable diffusion model InstructPix2Pix on the same data as their method for comparison, they found that Alchemist achieved superior accuracy scores. Likewise, a user study revealed that the MIT model was preferred and seen as more photorealistic than its counterpart.

Keeping it real with synthetic data

According to the researchers, collecting real data was impractical. Instead, they trained their model on a synthetic dataset, randomly editing the material attributes of 1,200 materials applied to 100 publicly available, unique 3D objects in Blender, a popular computer graphics design tool. “The control of generative AI image synthesis has so far been constrained by what text can describe,” says Frédo Durand, the Amar Bose Professor of Computing in the MIT Department of Electrical Engineering and Computer Science (EECS) and CSAIL member, who is a senior author on the paper. “This work opens new and finer-grain control for visual attributes inherited from decades of computer-graphics research.” "Alchemist is the kind of technique that's needed to make machine learning and diffusion models practical and useful to the CGI community and graphic designers,” adds Google Research senior software engineer and co-author Mark Matthews. “Without it, you're stuck with this kind of uncontrollable stochasticity. It's maybe fun for a while, but at some point, you need to get real work done and have it obey a creative vision."

Sharma’s latest project comes a year after he led research on Materialistic , a machine-learning method that can identify similar materials in an image. This previous work demonstrated how AI models can refine their material understanding skills, and like Alchemist, was fine-tuned on a synthetic dataset of 3D models from Blender.

Still, Alchemist has a few limitations at the moment. The model struggles to correctly infer illumination, so it occasionally fails to follow a user’s input. Sharma notes that this method sometimes generates physically implausible transparencies, too. Picture a hand partially inside a cereal box, for example — at Alchemist’s maximum setting for this attribute, you’d see a clear container without the fingers reaching in. The researchers would like to expand on how such a model could improve 3D assets for graphics at scene level. Also, Alchemist could help infer material properties from images. According to Sharma, this type of work could unlock links between objects' visual and mechanical traits in the future.

MIT EECS professor and CSAIL member William T. Freeman is also a senior author, joining Varun Jampani, and Google Research scientists Yuanzhen Li PhD ’09, Xuhui Jia, and Dmitry Lagun. The work was supported, in part, by a National Science Foundation grant and gifts from Google and Amazon. The group’s work will be highlighted at CVPR in June.

Share this news article on:

Related links.

• Frédo Durand
• William Freeman
• Prafull Sharma
• Computer Science and Artificial Intelligence Laboratory (CSAIL)
• Department of Electrical Engineering and Computer Science

Related Topics

• Artificial intelligence
• Computer science and technology
• Computer vision
• Computer graphics
• Electrical Engineering & Computer Science (eecs)

Related Articles

Using AI to protect against AI image manipulation

Researchers use AI to identify similar materials in images

Technique enables real-time rendering of scenes in 3D

Using computers to view the unseen

Previous item Next item

More MIT News

Exotic black holes could be a byproduct of dark matter

Read full story →

The unexpected origins of a modern finance tool

Nuh Gedik receives 2024 National Brown Investigator Award

Reducing carbon emissions from long-haul trucks

Mouth-based touchpad enables people living with paralysis to interact with computers

Advocating for science funding on Capitol Hill

• More news on MIT News homepage →

Massachusetts Institute of Technology 77 Massachusetts Avenue, Cambridge, MA, USA

• Map (opens in new window)
• Events (opens in new window)
• People (opens in new window)
• Careers (opens in new window)
• Accessibility
• Social Media Hub
• MIT on Facebook
• MIT on YouTube
• MIT on Instagram

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

AI Will Increase the Quantity — and Quality — of Phishing Scams

• Fredrik Heiding,
• Bruce Schneier,
• Arun Vishwanath

How businesses can prepare now.

Gen AI tools are rapidly making these emails more advanced, harder to spot, and significantly more dangerous. Recent research showed that 60% of participants fell victim to artificial intelligence (AI)-automated phishing, which is comparable to the success rates of non-AI-phishing messages created by human experts. Companies need to: 1) understand the asymmetrical capabilities of AI-enhanced phishing, 2) determine the company or division’s phishing threat severity level, and 3) confirm their current phishing awareness routines.

Anyone who has worked at a major organization has likely had to do training on how to spot a phishing attack — the deceptive messages that pretend to be from legitimate sources and aim to trick users into giving away personal information or clicking on harmful links. Phishing emails often exploit sensitive timings and play on a sense of urgency, such as urging the user to update a password. But unfortunately for both companies and employees, gen AI tools are rapidly making these emails more advanced, harder to spot, and significantly more dangerous.

• FH Fredrik Heiding is a research fellow in computer science at Harvard John A. Paulson School of Engineering and Applied Sciences and a teaching fellow for the Generative AI for Business Leaders course at the Harvard Business School. He researches how to mitigate AI-enabled cyberattacks via technical innovations, organizational strategies, and national security policies. Fredrik also works with the World Economic Forum’s Cybercrime Center to improve cybersecurity standards of AI-based cyber defense.
• Bruce Schneier is an internationally renowned security technologist, called a “security guru’ by the Economist. He is the New York Times best-selling author of 14 books — including A Hacker’s Mind — as well as hundreds of articles, essays, and academic papers. His influential newsletter Crypto-Gram and blog Schneier on Security are read by over 250,000 people. Schneier is a fellow at the Berkman-Klein Center for Internet and Society at Harvard University, a Lecturer in Public Policy at the Harvard Kennedy School, a board member of the Electronic Frontier Foundation and AccessNow, and an advisory board member of EPIC and VerifiedVoting.org. He is the Chief of Security Architecture at Inrupt, Inc.
• AV Arun Vishwanath , PhD, MBA, is a distinguished scholar and practitioner at the forefront of addressing cybersecurity’s “people problem” who has contributed commentary Wired , CNN, and The Washington Post . A former fellow at Harvard University’s Berkman Klein Center, he is the founder of the Cyber Hygiene Academy and serves as a distinguished expert for the NSA’s Science of Security & Privacy directorate. He is the author of the book The Weakest Link , published by MIT Press.

Partner Center

The state of AI in early 2024: Gen AI adoption spikes and starts to generate value

If 2023 was the year the world discovered generative AI (gen AI) , 2024 is the year organizations truly began using—and deriving business value from—this new technology. In the latest McKinsey Global Survey  on AI, 65 percent of respondents report that their organizations are regularly using gen AI, nearly double the percentage from our previous survey just ten months ago. Respondents’ expectations for gen AI’s impact remain as high as they were last year , with three-quarters predicting that gen AI will lead to significant or disruptive change in their industries in the years ahead.

About the authors

This article is a collaborative effort by Alex Singla , Alexander Sukharevsky , Lareina Yee , and Michael Chui , with Bryce Hall , representing views from QuantumBlack, AI by McKinsey, and McKinsey Digital.

Organizations are already seeing material benefits from gen AI use, reporting both cost decreases and revenue jumps in the business units deploying the technology. The survey also provides insights into the kinds of risks presented by gen AI—most notably, inaccuracy—as well as the emerging practices of top performers to mitigate those challenges and capture value.

AI adoption surges

Interest in generative AI has also brightened the spotlight on a broader set of AI capabilities. For the past six years, AI adoption by respondents’ organizations has hovered at about 50 percent. This year, the survey finds that adoption has jumped to 72 percent (Exhibit 1). And the interest is truly global in scope. Our 2023 survey found that AI adoption did not reach 66 percent in any region; however, this year more than two-thirds of respondents in nearly every region say their organizations are using AI. 1 Organizations based in Central and South America are the exception, with 58 percent of respondents working for organizations based in Central and South America reporting AI adoption. Looking by industry, the biggest increase in adoption can be found in professional services. 2 Includes respondents working for organizations focused on human resources, legal services, management consulting, market research, R&D, tax preparation, and training.

Also, responses suggest that companies are now using AI in more parts of the business. Half of respondents say their organizations have adopted AI in two or more business functions, up from less than a third of respondents in 2023 (Exhibit 2).

Gen AI adoption is most common in the functions where it can create the most value

Most respondents now report that their organizations—and they as individuals—are using gen AI. Sixty-five percent of respondents say their organizations are regularly using gen AI in at least one business function, up from one-third last year. The average organization using gen AI is doing so in two functions, most often in marketing and sales and in product and service development—two functions in which previous research  determined that gen AI adoption could generate the most value 3 “ The economic potential of generative AI: The next productivity frontier ,” McKinsey, June 14, 2023. —as well as in IT (Exhibit 3). The biggest increase from 2023 is found in marketing and sales, where reported adoption has more than doubled. Yet across functions, only two use cases, both within marketing and sales, are reported by 15 percent or more of respondents.

Gen AI also is weaving its way into respondents’ personal lives. Compared with 2023, respondents are much more likely to be using gen AI at work and even more likely to be using gen AI both at work and in their personal lives (Exhibit 4). The survey finds upticks in gen AI use across all regions, with the largest increases in Asia–Pacific and Greater China. Respondents at the highest seniority levels, meanwhile, show larger jumps in the use of gen Al tools for work and outside of work compared with their midlevel-management peers. Looking at specific industries, respondents working in energy and materials and in professional services report the largest increase in gen AI use.

Investments in gen AI and analytical AI are beginning to create value

The latest survey also shows how different industries are budgeting for gen AI. Responses suggest that, in many industries, organizations are about equally as likely to be investing more than 5 percent of their digital budgets in gen AI as they are in nongenerative, analytical-AI solutions (Exhibit 5). Yet in most industries, larger shares of respondents report that their organizations spend more than 20 percent on analytical AI than on gen AI. Looking ahead, most respondents—67 percent—expect their organizations to invest more in AI over the next three years.

Where are those investments paying off? For the first time, our latest survey explored the value created by gen AI use by business function. The function in which the largest share of respondents report seeing cost decreases is human resources. Respondents most commonly report meaningful revenue increases (of more than 5 percent) in supply chain and inventory management (Exhibit 6). For analytical AI, respondents most often report seeing cost benefits in service operations—in line with what we found last year —as well as meaningful revenue increases from AI use in marketing and sales.

Inaccuracy: The most recognized and experienced risk of gen AI use

As businesses begin to see the benefits of gen AI, they’re also recognizing the diverse risks associated with the technology. These can range from data management risks such as data privacy, bias, or intellectual property (IP) infringement to model management risks, which tend to focus on inaccurate output or lack of explainability. A third big risk category is security and incorrect use.

Respondents to the latest survey are more likely than they were last year to say their organizations consider inaccuracy and IP infringement to be relevant to their use of gen AI, and about half continue to view cybersecurity as a risk (Exhibit 7).

Conversely, respondents are less likely than they were last year to say their organizations consider workforce and labor displacement to be relevant risks and are not increasing efforts to mitigate them.

In fact, inaccuracy— which can affect use cases across the gen AI value chain , ranging from customer journeys and summarization to coding and creative content—is the only risk that respondents are significantly more likely than last year to say their organizations are actively working to mitigate.

Some organizations have already experienced negative consequences from the use of gen AI, with 44 percent of respondents saying their organizations have experienced at least one consequence (Exhibit 8). Respondents most often report inaccuracy as a risk that has affected their organizations, followed by cybersecurity and explainability.

Our previous research has found that there are several elements of governance that can help in scaling gen AI use responsibly, yet few respondents report having these risk-related practices in place. 4 “ Implementing generative AI with speed and safety ,” McKinsey Quarterly , March 13, 2024. For example, just 18 percent say their organizations have an enterprise-wide council or board with the authority to make decisions involving responsible AI governance, and only one-third say gen AI risk awareness and risk mitigation controls are required skill sets for technical talent.

Bringing gen AI capabilities to bear

The latest survey also sought to understand how, and how quickly, organizations are deploying these new gen AI tools. We have found three archetypes for implementing gen AI solutions : takers use off-the-shelf, publicly available solutions; shapers customize those tools with proprietary data and systems; and makers develop their own foundation models from scratch. 5 “ Technology’s generational moment with generative AI: A CIO and CTO guide ,” McKinsey, July 11, 2023. Across most industries, the survey results suggest that organizations are finding off-the-shelf offerings applicable to their business needs—though many are pursuing opportunities to customize models or even develop their own (Exhibit 9). About half of reported gen AI uses within respondents’ business functions are utilizing off-the-shelf, publicly available models or tools, with little or no customization. Respondents in energy and materials, technology, and media and telecommunications are more likely to report significant customization or tuning of publicly available models or developing their own proprietary models to address specific business needs.

Respondents most often report that their organizations required one to four months from the start of a project to put gen AI into production, though the time it takes varies by business function (Exhibit 10). It also depends upon the approach for acquiring those capabilities. Not surprisingly, reported uses of highly customized or proprietary models are 1.5 times more likely than off-the-shelf, publicly available models to take five months or more to implement.

Gen AI high performers are excelling despite facing challenges

Gen AI is a new technology, and organizations are still early in the journey of pursuing its opportunities and scaling it across functions. So it’s little surprise that only a small subset of respondents (46 out of 876) report that a meaningful share of their organizations’ EBIT can be attributed to their deployment of gen AI. Still, these gen AI leaders are worth examining closely. These, after all, are the early movers, who already attribute more than 10 percent of their organizations’ EBIT to their use of gen AI. Forty-two percent of these high performers say more than 20 percent of their EBIT is attributable to their use of nongenerative, analytical AI, and they span industries and regions—though most are at organizations with less than $1 billion in annual revenue. The AI-related practices at these organizations can offer guidance to those looking to create value from gen AI adoption at their own organizations.

To start, gen AI high performers are using gen AI in more business functions—an average of three functions, while others average two. They, like other organizations, are most likely to use gen AI in marketing and sales and product or service development, but they’re much more likely than others to use gen AI solutions in risk, legal, and compliance; in strategy and corporate finance; and in supply chain and inventory management. They’re more than three times as likely as others to be using gen AI in activities ranging from processing of accounting documents and risk assessment to R&D testing and pricing and promotions. While, overall, about half of reported gen AI applications within business functions are utilizing publicly available models or tools, gen AI high performers are less likely to use those off-the-shelf options than to either implement significantly customized versions of those tools or to develop their own proprietary foundation models.

What else are these high performers doing differently? For one thing, they are paying more attention to gen-AI-related risks. Perhaps because they are further along on their journeys, they are more likely than others to say their organizations have experienced every negative consequence from gen AI we asked about, from cybersecurity and personal privacy to explainability and IP infringement. Given that, they are more likely than others to report that their organizations consider those risks, as well as regulatory compliance, environmental impacts, and political stability, to be relevant to their gen AI use, and they say they take steps to mitigate more risks than others do.

Gen AI high performers are also much more likely to say their organizations follow a set of risk-related best practices (Exhibit 11). For example, they are nearly twice as likely as others to involve the legal function and embed risk reviews early on in the development of gen AI solutions—that is, to “ shift left .” They’re also much more likely than others to employ a wide range of other best practices, from strategy-related practices to those related to scaling.

In addition to experiencing the risks of gen AI adoption, high performers have encountered other challenges that can serve as warnings to others (Exhibit 12). Seventy percent say they have experienced difficulties with data, including defining processes for data governance, developing the ability to quickly integrate data into AI models, and an insufficient amount of training data, highlighting the essential role that data play in capturing value. High performers are also more likely than others to report experiencing challenges with their operating models, such as implementing agile ways of working and effective sprint performance management.

About the research

The online survey was in the field from February 22 to March 5, 2024, and garnered responses from 1,363 participants representing the full range of regions, industries, company sizes, functional specialties, and tenures. Of those respondents, 981 said their organizations had adopted AI in at least one business function, and 878 said their organizations were regularly using gen AI in at least one function. To adjust for differences in response rates, the data are weighted by the contribution of each respondent’s nation to global GDP.

Alex Singla and Alexander Sukharevsky  are global coleaders of QuantumBlack, AI by McKinsey, and senior partners in McKinsey’s Chicago and London offices, respectively; Lareina Yee  is a senior partner in the Bay Area office, where Michael Chui , a McKinsey Global Institute partner, is a partner; and Bryce Hall  is an associate partner in the Washington, DC, office.

They wish to thank Kaitlin Noe, Larry Kanter, Mallika Jhamb, and Shinjini Srivastava for their contributions to this work.

This article was edited by Heather Hanselman, a senior editor in McKinsey’s Atlanta office.

Explore a career with us

Related articles.

Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale

A generative AI reset: Rewiring to turn potential into value in 2024

Implementing generative AI with speed and safety

Best Free AI Training Courses You Can Take in June 2024

The artificial intelligence hype cycle has continued long enough: It might just be time to learn a thing or two about the latest technology trend that’s been impacting every business industry at the same time for a couple years now.

If you’re the average person, however, that’s easier said than done. Figuring out AI — or at least, figuring out how to use it within your job role , whatever that may be — can be an overwhelming task. So, we’ve rounded up the top AI training courses to check out.

We’ve covered the best essential AI courses in the past, but there are plenty of options to chose from, all ranging in the amount of time required and the type of knowledge you’ll gain. Here are the best courses to know about in June 2024.

Get the latest tech news, straight to your inbox

Stay informed on the top business tech stories with Tech.co's weekly highlights reel.

By signing up to receive our newsletter, you agree to our Privacy Policy . You can unsubscribe at any time.

IBM: Generative AI for Everyone

⏰ Length: 4-8 hours

IBM is a big brand in the technology space, so its just-the-basics explainer course is a good starting point for anyone who’s serious about figuring out how AI works, what applications it has to offer, and what use cases you can try it for.

This course is a self-paced training session, although the creators estimate it’ll take about four weeks, with just 1-2 hours of work per week. It covers AI terms including Machine Learning, Deep Learning, and Neural Networks; It tackles the ethical concerns to know about the nascent technology; and it comes with advice from top experts about careers within the AI world.

To get started, head over to edX and sign up for the completely free course . You’ll even get a badge upon completion, and it’s subtitled with a wide range of languages — including Deutsch, Español, Français, and Português, among others.

Introduction to AI for Business Users

⏰ Length: About 2 hours

Looking for the fastest way to get fully up to speed on using AI for business cases? If you’re using the Microsoft 365 business suite, look no further than this quick 2-hour course. It’s an accessible way to understand the benefits of artificial intelligence for everyone who doesn’t have a deep STEM background.

This course is specific to learning the Microsoft Power Platform and how to use the technology to craft reports and dashboards that take advantage of AI-powered data insights. It’s far from a broad application of AI, but Microsoft platforms loom large in the business world, so you’ll likely have plenty of chances to flex your skills and impress everyone with your AI know-how. Best of all, it will only take an afternoon to complete.

You can check out the course and others today, straight from the Microsoft website.

Stanford: Machine Learning Specialization

⏰ Length: 80 hours

With this series, you’ll learn from Stanford University’s Andrew Ng over  three courses, all covering the ins and outs of machine learning. It’s an updated version of a course that first launched in 2012 and has been rated 4.9 out of 5 by a total of more than 4.8 million viewers since then, so it comes highly recommended.

It’s billed as a path towards helping students “break into AI or build a career in machine learning,” or at least get them started on that process. You’ll gain a better understanding of modern machine learning, complete with supervised and unsupervised learning, as well as machine learning innovation best practices like “evaluating and tuning models, taking a data-centric approach to improving performance, and more.”

It’s about two months long, for those who take 10 hours a week, and like most free online courses, you’ll be able to study at your own pace. Check it out now on the Coursera website.

HarvardX: CS50’s Introduction to Artificial Intelligence with Python

⏰ Length: 70-210 hours

Learning the basics of AI is great, but sometimes it pays off to jump into a much more specific training course: You’ll learn actionable skills that can directly translate to an AI-related position within a coding field you already have an understanding of.

If you know Python, than this course might be for you. It’ll cover machine learning within that programming language and at seven weeks for 10-30 hours per week, this course won’t be easy. But you’ll emerge with knowledge of a laundry list of concepts that include graph search algorithms, adversarial search, logical inference, probability theory, Bayesian networks, Markov models and a whole lot more.

Head over to edX to sign up for the course or to learn more about the specifics.

LinkedIn: How to Research and Write Using Generative AI Tools

⏰ Length: 5 hours

Boosting research and writing is a pro that plenty of generative AI bots like ChatGPT claim they can do. In practice, it’s not so easy, since you’ll need to figure out the pitfalls of prompt engineering and tweaking your results to actually get a clean, well-composed answer in response.

LinkedIn is here to help, with a course that landed smack at the top of the social platform’s top ten list of the best courses available on its LinkedIn Learning website. Led by Dave Birss, the course will take users through how to interact with generative AI bots with prompts. You’ll avoid getting bogged down in technical knowledge, but you’ll learn fascinating facts. Did you know saying “please” gets you better results when interacting with an AI?

Check out the full course over at LinkedIn, where it’s available free , as long as you sign up for a free month-long trial.

Diving Into AI Learning

For now, at least, AI technology is a helpful tool, and learning a few things about it can easily put you well ahead of the majority of workers out there. If you’re anticipating a change in your career, are job-seeking now, or just want to have something to point to when your next annual review rolls around, you can definitely do a lot worse than one of the courses listed above.

But if you want an even quicker catch-up, we’ve got you covered. Check out some of our previous AI coverage here at Tech.co to learn more quick tips on how to write the best prompts , which GPT bots are actually helpful , or even how to create a resume template with AI.

Just don’t forget the downsides to AI: You should always be wary of the possibility for hallucinations and the cybersecurity risks or legal problems that can accompany them. AI might be the hot new trend, but it’s far from a perfect technology.

Stay informed on the top business tech stories with Tech.co's weekly highlights reel.

We're sorry this article didn't help you today – we welcome feedback, so if there's any way you feel we could improve our content, please email us at [email protected]

• Artificial Intelligence

Written by:

Nvidia Has Announced Another New AI Chip

The announcement comes just three months after its latest...

What Are Remote AI Training Jobs and How Do You Get One?

All these chatbots need to learn how to interact with...

This Easy Google Hack Removes AI Results and Adverts from Search

Reminiscing on how Google looked a decade ago? Remove the...

Essential Free AI Training Courses You Can Take in May 2024

Build your AI skills this month, with these free training...