Artificial Intelligence (AI) and the literature review process: Tools

Application of AI tools such as ChatGPT to searching and all aspects of the literature review process

This page lists the AI tools recommended to conduct a literature review:

Click the use-cases links for instructions and examples of prompts.

Generic AI Chatbots

AI companies initially adopted a chat interface to allow the public to interact with language models from a Web browser. Below, we review popular AI chatbots' main characteristics and use cases in the context of a literature review:

 

Microsoft Copilot

Input: Text, voice, image files.

Notable features: Connected to the Internet, references sources in its answers, 3 levels of verbosity.

Use casesabstract and title creationscoping, searching.

Cost: free or included in Microsoft 365 plans.

Limits: Number of allowed chats per day varies depending on the load and MS 365 plan.

History: Microsoft's Copilot (former Bing Chat) is an AI-based research assistant powered by OpenAi's GPT-4. Copilot also designates the generative AI features integrated into Microsoft 365 apps such as Word, Excel, Powerpoint, Teams and ClipChamp.

Privacy and legal information

 

Copilot


 

Chat GPT

Version 3.5

Input: Text

Notable features: 175 billion parameters model.

Use cases: abstract and title creationscoping

Cost: free

Limits: Open AI documentation > Rate limits > Usage tiers

History: ChatGPT launched in November 2022. It was been built on top of OpenAI’s GPT-3 family of large language models (Generative Pre-trained Transformer) and was fine-tuned using both supervised and reinforcement learning techniques (OpenAI, 2022).

It is estimated to have reached 100 million monthly active users in January 2023, just two months after launch, making it the fastest-growing consumer application in history (Hu, 2023).

 

Version 4

Input: Text, files, images and sound.

Notable features: Connected to internet, can access databases and websites through plugins.

Use cases: abstract and title creationscoping, searching.

Cost: Requires a subscription.

Limits: Open AI documentation > Rate limits > Usage tiers

History: OpenAI launched ChatGPT4 in March 2023. GPT-4 is a model based on transformer architecture pre-trained to predict the next token in a document, using both publicly available data (such as internet data) and data licensed from third-party providers. The model was then fine-tuned using Reinforcement Learning from Human Feedback (RLHF). As the technical report states, "given both the competitive landscape and the safety implications of large-scale models like GPT-4, this report contains no further details about the architecture (including model size), hardware, training computer,dataset, construction, training method, or similar" (OpenAI, 2023).

Privacy and legal information

 

 

ChatGPT


 

Claude.ai

Input: Text, files

Notable features: generates safe answers, supports large prompts, accepts text files attached to a prompt.

Use cases: abstract and title creation, scoping.

Cost: Claude.ai is free, Claude Pro requires a subscription.

Limits: The daily message limit varies depending on the demand and the subscription tier (Anthropic, 2024) .

History: Claude 2 is the second iteration of the foundational model created by Anthropic. Claude 2 states it is "an AI assistant focused on being helpful, harmless, and honest" that "aims to have conversations in an ethical way, without mentioning inappropriate topics."

Claude 2 can handle large prompts (up to 100k tokens) which means it can work with whole documents such as books.

Privacy and legal information

 

Claude AI


 

Gemini

Input: Text, images, voice.

Notable features: Optimised for summarising, reasoning, coding, and planning. Dataset continuously updated from the Web. Extensions allow Gemini to access personnal data and 3rd party services.

Limits: Cannot search the web. Can cite references when asked.

Use cases: abstract and title creation, scoping.

Cost: Gemini Pro is free, Gemini Ultra requires a fee.

History: "Gemini is Google's most advanced AI model, built from the ground up to be multimodal, which means it can generalize and seamlessly understand, operate across and combine different types of information including text, code, audio, image and video. You will need a personal Google account that you manage on your own to access Gemini. Google's Gemini model will also be included in Google's Pixel 8 Pro, the first smartphone engineered to run Gemini Nano, powering new features such as Summarize in the Recorder app and Smart Reply in Gboard. The Gemini model appears in the Google search engine in the USA as an early stage experience that you can opt into to get AI-powered overviews and ask follow-up questions" (see Google's 25 May 2023 blog). Previously known as Bard, the Gemini family includes its Pro 1.0 model, Gemini Advanced, available on subscription, and a mobile app (see its 8 February 2024 blog). A UK release is yet to be announced.

Privacy and legal information

 

Gemini


 

 

Academic Research Tools

These tools assist researchers with searching, analysing and visualising academic publications:

Follow the use cases links for guidance and examples applying to conducting a literature review.

Connected Papers

connected papers logoConnected Papers (Smolyansky, 2020) is based on the Semantic Scholar database. Its premise is that two papers that have highly overlapping citations and references are presumed to have a higher chance of treating a related subject matter. The graphs that are produced are designed to highlight the most important and relevant papers immediately. You will only get 5 graphs per month for free.

Use cases: visualising search results, finding similar work.

Limits: You will only get 5 graphs per month for free.

Privacy policy.

Connected Papers


 

Elicit

Elicit logoElicit will do this for you saving you time and allowing you to then synthesise the information. Its own user survey found that 10% of respondents said that Elicit saves them 5 or more hours each week and that, in pilot projects, Elicit saved research groups 50% in costs and more than 50% in time by automating data extraction work they previously did manually (Elicit, 2023).

The free basic version allows you to extract data from papers and upload your own papers. However, only priced versions of the product will give you summaries of papers and allow you to extract the information into csv and bib formats.

Use case: Data Extraction.

Privacy policy.

Elicit: AI research assistant


 

Inciteful.xyz

Inciteful logoInciteful.xyz has pulled information and/or inspiration from Semantic Scholar but also three other data sources: OpenAlex, CrossRef and OpenCitations. It has used these sources to help researchers get up to speed on a new topic, to find the latest literature or to work out how two ideas are connected (Weishuhn, 2024). There are two tools that are under active development: Paper Discovery and the Literature Connector. Paper Discovery builds a network of papers from citations, analyses the network, and allows you to get up to speed on a topic.  by finding the most similar papers, important papers as well as prolific authors and institutions. Literature Connector allows you to enter two papers and it will give you an interactive visualization show you how they are connected by the literature.

Use case: visualising search results.

Inciteful.xyz


 

LitMaps

LitMaps logoLitMaps is also based on the Semantic Scholar database. As with the above, it uses the citation network to construct graphs to visualise the research landscape of your topic. Its Discover tool enables you to find gaps in your own literature reviews and to upload existing literature reviews to find not only more recent papers but also papers that the reviews may have missed.

Use cases: visualising search results.

Privacy policy.

LitMaps


 

Rayyan AI

Rayyan AI is a web-based automated screening tool, developed by Qatar Computing Research Institute (QCRI), which launched in 2014.

It uses text mining techniques to identify relevant information using statistical pattern learning that recognises patterns in the data.

Use case: Screening.

Privacy policy

Rayyan AI


 

Research Rabbit

Research Rabbit logoResearch Rabbit also uses Semantic Scholar to search for papers but also uses PubMed to find biomedical and life sciences papers. It is committed to remaining free to researchers.

Use cases: visualising search results.

Privacy policy

ResearchRabbit


 

SciteAI

scite logoSciteAI, designed by Nicholson et al. (2021), categorizes citations according to whether the articles were contrasting, supporting or mentioning. Scite.ai is very keen for you to take a 7 day free trial but will provide you with a certain amount of free information that you can use for critical evaluation.

Use case: Synthesis.

Privacy policy

 

Scite.ai


 

Semantic Scholar

Semantic Scholar logoSemantic Scholar is a free, AI-powered search and discovery tool that helps researchers discover and understand scientific literature most relevant to their work.

Semantic Scholar sources its content via web indexing and from partnerships with scientific journals, indexes, and content providers. These include leading publishers such as Springer Nature, Taylor & Francis, Wiley and Sage and institutions such as the IEEE and ACM. It does not contain content from Elsevier, Emerald or Oxford University Press. There is a list of its publisher partners.

Semantic Scholar does not support Boolean searching or wildcards. Its tutorial pages tell you that Semantic Scholar covers papers across all subjects including biomedicine, computer science, business, history, and economics. Its Ask This Paper and Generative Term Understanding features employ generative AI.

Use cases: Searching.

Privacy policy

Semantic Scholar