Skip to Main Content

Literature Discovery through Citation Chaining and Mapping: Undermind

A quick guide to introduce citation chaining and mapping tools for literature discovery

Undermind - About

Undermind is a new AI tool designed for exhaustive literature search, based on a detailed research question in natural language. Unlike typical citation mapping tools, it leverages both LLMs and citation mapping techniques for literature discovery.

Undermind can help you (these features are limited to Pro users, starting Jun 2024):

  • Generate 100 papers in the initial run; papers are ranked by their “topic match score”. 
  • Create a timeline map of these papers ("the highlighted papers are precisely relevant to your exact topic").

It also categorizes all articles into a few subject categories, allowing researchers to navigate the literature more efficiently and focus on specific aspects relevant to their question. 

Undermind - Demo

Update note (Jun 2024): Retrieval of 100 papers and citation mapping feature are now limited to Pro users only. Free users can retrieve the top 5 papers only. 

How to Read the "Map"

(Jun 2024) Citation mapping limited to Pro users now.

  • Each node: one paper
  • Node size: "relevance score" to the topic (combines topic match score and the centrality of the paper in the citation network)
  • Node color: 
    • Green: analyzed papers
    • Black: other papers
  • (when selected a paper)
    • Dark grey: selected paper
    • Orange: papers cited in the selected paper
    • Blue: papers citing the selected paper


  • x-axis: publication date (more recent on the right)
  • y-axis: relative citation influence of a paper on the topic (papers move up if they are referenced by most papers on the topic; papers move down if they are citing most papers on the topic.)
© HKUST Library, The Hong Kong University of Science and Technology. All Rights Reserved.