Skip to Main Content

Generative AI for Research

This Research Guide provides information on the use of Generative AI in academic papers and research, and provides guidance on the ethical use of Generative AI in an academic setting.

Examples of generative AI that can support research discovery and generate explanations include: ElicitResearch Rabbit, and Scite.

- Please note that some databases available at CWC also use AI to help generate search results.

Research Tools

What is Elicit?

Elicit: The AI Research Assistant

Elicit, developed by Ought, is an AI tool to find 'seed articles' and to  mine for keywords/subject headings.  When you enter a question, it returns alternate questions that can lead to further "seed" articles.

Sign up for a free account 

Searching Features:

  • Elicit uses language models to help you automate research workflows, like parts of literature review.
  • Elicit can find relevant papers without perfect keyword match, summarize takeaways from the paper specific to your question, and extract key information from the papers.
  • While answering questions with research is the main focus of Elicit, there are also other research tasks that help with brainstorming, summarization, and text classification.
  • You can save and export your work to citation managers such as Zotero.

FAQs from Elicit

Videos:

What is ResearchRabbit?

ResearchRabbit paper mapping

ResearchRabbit is an innovative “citation-based literature mapping tool” available online. The scope of such tool is to optimize your time searching for references as you start planning your essay, minor project, or literature review. The concept is simple: you start by using one or more papers (called seed papers), and the app will find more papers relevant to the topic of interest (which is dictated by the seed papers you previously selected).

The tool is designed to support your research without you switching between searching modes and databases, a process that is time consuming and often escalates into further citation mining; a truly unpleasant rabbit hole (and that’s what inspired the name ResearchRabbit)!

Sign up for a Free Account 

Searching Features:

  • ResearchRabbit uses a method of Seed-based Literature Discovery: a user starts with a few papers they have already found and RR recommends related works - via co-citation, shared authorship, or research topic.
  • ResearchRabbit allows users to visually see how papers are related to each other.
  • ResearchRabbit allows users to organize and curate papers, take notes and highlight, and track their search history.
  • ResearchRabbit is ideal for early-stage literature reviews, tracking fast moving fields, collaborating on research projects, or identifying key papers or authors in a discipline.

ResearchRabbit FAQs:

FAQ

Tips and Tricks

Product Overview

Video Tutorials

What is Scite?

Scite Full Text Processing

Scite is an AI-powered research tool designed to enhance literature discovery and citation analysis. Its key feature, Smart Citation, shows the context in which an article is cited and whether it offers supporting or contrasting evidence. This helps users quickly assess the relevance and impact of academic sources.

Scite also includes Assistant, a generative AI feature that answers research questions by summarizing recent academic literature and providing source references. While helpful for overviews, it is intended as a starting point rather than a replacement for a full literature review.

Scite partners with major publishers and preprint servers to offer a broad, high-quality index of academic papers. 

Searching Features:

  • See and read each and every citation that was made to this paper by others.
  • Get aggregate information about the number of citations made, disaggregated by each classification type from our deep learning model.
  • Filter citations by additional attributes such as the section in the citing paper where the citation occurred, or whether the citing publication was a book, research paper, preprint, etc.
  • Search directly within the extracted text snippets to find relevant citations.

How does Scite Work?

Scite processes full-text articles to build out its database of Smart Citations, which contain information about:

  • which papers are citing each other
  • the textual context of each citation and the location within the citing paper
  • a classification describing whether the citation is supporting, mentioning, or contrasting the cited work's claims

This source of data is used to build a variety of features. For example, you can find the scite report for a given paper and:

  • see and read each and every citation that was made to this paper by others
  • get aggregate information about the number of citations made, dis-aggregated by each classification type from our deep learning model
  • filter citations by additional attributes such as the section in the citing paper where the citation occurred, or whether the the citing publication was a book, research paper, preprint, etc.
  • search directly within the extracted text snippets to find relevant citations

Scite FAQs