Skip to Main Content

AI for Literature Reviews

This guide provides a list of artificial intelligence (ai) tools that are helpful for literature reviews

AI Summary Tools

  • Elicit searches across over 126 million academic papers from the Semantic Scholar corpus across all academic disciplines.
  • Only research articles, doesn't contain books
  • Includes non-open access articles and pre-prints
  • Summarizes first four abstracts
  • Allows users to:
    • Find papers
    • Extract data from PDF
    • Build a list of concepts
    • Screen papers for inclusion
  • Can extract different types of data: Summary, main findings, methodology, intervention, outcome measured, limitations, and custom
  • Integrates with Zotero
  • Free and paid version (10$/month)

Screenshot of Elicit's homepage

  • SciSpace provides summaries of top papers, insights, conclusions, and practical implications
  • For every paper you read, get simple explanations and answers from AI and discover a network of connected and relevant papers
  • Metadata of 200 million+ papers and 50 million+ Open Access full-text PDFs
  • Contains a citation generator, paraphraser (write in many tones), ai detector
  • Contains an ai "co-pilot", a generated ai tool
  • Can extract different types of data: conclusions, summarized abstract, TL;DR, results, summarised introduction,  methods used, literature survey, limitations, contributions, practical implications
  • Can summarize, explain text/math, get related papers, highlight text of PDFs
  • Contains a ChatGPT detector
  • Has a Google Chrome extension 
  • Free and paid (10$-12$) version

Screenshot of homepage of SciSpace

  • scite is a tool which offers a quantitative and qualitative insight into how scientific publications cite each other.
  • scite helps with some of the major aspects of performing literature reviews and critical analysis including: critically engaging with publications, understanding how a publication and its results have been cited, and finding relevant literature on the topic in question.
  • 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
  • Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence
  • Search over 1.2b+ citation statements to see what is being said about any topic in the research literature
  • Citation reports and visualizations to easily see what publications are saying about each other
  • Zotero and Chrome plugins
  • Free and paid (20$/month) versions
  • Consensus is a search engine that uses language models to surface papers and synthesize insights from academic research papers.
  • The current source material used in Consensus comes from the Semantic Scholar database, which includes over 200M papers across all domains of science.
  • Produces a list of the most relevant papers to your question and a key insight or conclusion from that paper.
  • Consensus will pull out snippets from papers related to your question
  • Consensus instead uses “extractive” methods to pull out word-for-word quotes from papers in response to the user’s question.
  • Connects to SciSpace
  • Integrates with Zotero
  • Free and paid (6.99$/month) versions

Screenshot of Consensus homepage

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.