Abstract
Elicit is an online tool developed by Ought, a non-profit machine learning (ML) research lab based in the United States. It is a free artificial intelligence (AI) research assistant that "uses language models to automate part of researchers' workflows" [1]. Ideal for evidence synthesis and text extraction, Elicit pulls publications from Semantic Scholar and expedites the literature review process. Users enter a research question into the search box and the AI attempts to identify the top papers in the field. The AI can find relevant papers without perfect keyword matching, summarize takeaways from the paper, and extract key information into a research matrix. Taking inspiration from the systematic review process, the language model retrieves and condenses the information into component parts, thus allowing users to filter topics from a paper's abstract including a shortened version of the abstract, intervention, outcomes, number of participants, population summary, and more. Elicit is ideal for questions that have empirical research (e.g., research in biomedicine) with interventions, randomized controlled trials, and questions generally structured as "What are the effects of x on y?" or "Does x affect y?" [2].
Cite
CITATION STYLE
Kung, J. (2023). Elicit (product review). Journal of the Canadian Health Libraries Association / Journal de l’Association Des Bibliothèques de La Santé Du Canada, 44(1). https://doi.org/10.29173/jchla29657
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.