DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration

TL;DR

DiscipLink is an interactive system that leverages large language models to assist researchers in navigating and integrating knowledge across disciplines during interdisciplinary literature searches.

Contribution

The paper introduces DiscipLink, a novel human-AI co-exploration tool designed to facilitate interdisciplinary information seeking and collaboration.

Findings

DiscipLink effectively supports breaking disciplinary boundaries.

Users find it easier to identify relevant interdisciplinary literature.

The system enhances understanding of connections between papers and research questions.

Abstract

Interdisciplinary studies often require researchers to explore literature in diverse branches of knowledge. Yet, navigating through the highly scattered knowledge from unfamiliar disciplines poses a significant challenge. In this paper, we introduce DiscipLink, a novel interactive system that facilitates collaboration between researchers and large language models (LLMs) in interdisciplinary information seeking (IIS). Based on users' topics of interest, DiscipLink initiates exploratory questions from the perspectives of possible relevant fields of study, and users can further tailor these questions. DiscipLink then supports users in searching and screening papers under selected questions by automatically expanding queries with disciplinary-specific terminologies, extracting themes from retrieved papers, and highlighting the connections between papers and questions. Our evaluation, comprising a within-subject comparative experiment and an open-ended exploratory study, reveals that DiscipLink can effectively support researchers in breaking down disciplinary boundaries and integrating scattered knowledge in diverse fields. The findings underscore the potential of LLM-powered tools in fostering information-seeking practices and bolstering interdisciplinary research.