Papers
arxiv:2408.15836

Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature

Published on Aug 28
· Submitted by Uri-ka on Aug 29
Authors:

Abstract

The exponential growth of scientific literature necessitates advanced tools for effective knowledge exploration. We present Knowledge Navigator, a system designed to enhance exploratory search abilities by organizing and structuring the retrieved documents from broad topical queries into a navigable, two-level hierarchy of named and descriptive scientific topics and subtopics. This structured organization provides an overall view of the research themes in a domain, while also enabling iterative search and deeper knowledge discovery within specific subtopics by allowing users to refine their focus and retrieve additional relevant documents. Knowledge Navigator combines LLM capabilities with cluster-based methods to enable an effective browsing method. We demonstrate our approach's effectiveness through automatic and manual evaluations on two novel benchmarks, CLUSTREC-COVID and SCITOC. Our code, prompts, and benchmarks are made publicly available.

Community

Paper author Paper submitter
This comment has been hidden
Paper author Paper submitter

Check out our paper, Knowledge Navigator. We have designed a new paradigm for browsing scientific literature. Using LLMs and clustering-based methods, we organize hundreds of scientific documents retrieved for a query into a table of contents structure. All documents are assigned to subtopics and primary themes, with each theme and subtopic named and summarized for the searcher. The output of this process is a browsing framework that enables navigation within a knowledge map instead of screening through hundreds of documents in a ranked list, allowing for exploration and discovery of trends and specific research questions. A demo is available on the paper’s website as well as the code and benchmarks. https://knowledge-navigators.github.io/

·

Hi @Uri-ka ,

Congrats on this work. Are you planning to share the benchmarks as HF datasets? See here for a guide: https://huggingface.co/docs/datasets/loading.

They can then also be linked to this paper, as explained here: https://huggingface.co/docs/hub/en/datasets-cards#linking-a-paper

Cheers!

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2408.15836 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2408.15836 in a Space README.md to link it from this page.

Collections including this paper 3