Literature Reviews
Literature Searching using Artificial Intelligence
Artificial Intelligence tools are fast-changing. Make sure to check each tool for features you are looking for.
Click the tool name below to jump directly there.
| ChatGPT | Elicit AI |
| Research Rabbit | Connected Papers |
| Semantic Scholar | NotebookLM |
www.researchrabbit.ai
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.

MORE RESOURCES
Video Introduction to Research Rabbit

https://elicit.org
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.
- 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
Enter a research question or multiple keywords about a research question.
Enter the title of a paper.
The stared or selected studies will lead to Semantic Scholar's site for detailed information for all citations. - 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
MORE RESOURCES
www.semanticscholar.org
A free, AI-powered research tool for scientific literature.
- Over 200 millions of papers from all fields of science.
- Example - nursing student mental health "scoping review"
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 -
Semantic Reader
"Semantic Reader is an augmented reader with the potential to revolutionize scientific reading by making it more accessible and richly contextual" . It "uses artificial intelligence to understand a document’s structure and merge it with the Semantic Scholar’s academic corpus, providing detailed information in context via tooltips and other overlays." <https://www.semanticscholar.org/product/semantic-reader>.
Skim Papers Faster
"Find key points of this paper using automatically highlighted overlays. Available in beta on limited papers for desktop devices only." <https://www.semanticscholar.org/product/semantic-reader>. Press on the pen icon to activate the highlights. -
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>