Multi-Disciplinary Dataset Discovery from Citation-Verified Literature Contexts

TL;DR

This paper presents a novel literature-driven framework that leverages citation contexts and large language models to improve dataset discovery in scientific literature, surpassing existing search engines in recall and uncovering additional valuable datasets.

Contribution

It introduces a new citation-context mining approach combined with schema-guided dataset recognition and entity resolution, enabling more effective dataset discovery from scientific texts.

Findings

Achieves higher recall than Google Dataset Search and DataCite Commons

Surfaces additional datasets not documented in surveys

Expert assessments indicate high utility and novelty of discovered datasets

Abstract

Identifying suitable datasets for a research question remains challenging because existing dataset search engines rely heavily on metadata quality and keyword overlap, which often fail to capture the semantic intent of scientific investigation. We introduce a literature-driven framework that discovers datasets from citation contexts in scientific papers, enabling retrieval grounded in actual research use rather than metadata availability. Our approach combines large-scale citation-context extraction, schema-guided dataset recognition with Large Language Models, and provenance-preserving entity resolution. We evaluate the system on eight survey-derived computer science queries and find that it achieves substantially higher recall than Google Dataset Search and DataCite Commons, with normalized recall ranging from an average of 47.47% to a highest value of 81.82%. Beyond recovering gold-standard datasets, the method also surfaces additional datasets not documented in the surveys. Expert assessments across five top-level Fields of Science indicate that a substantial portion of the additional datasets are considered high utility, and some are regarded as novel for the specific topics chosen by the experts. These findings establish citation-context mining as an effective and generalizable paradigm for dataset discovery, particularly in settings where datasets lack sufficient or reliable metadata. To support reproducibility and future extensions, we release our code, evaluation datasets, and results on GitHub (https://github.com/Fireblossom/citation-context-dataset-discovery).