# Multi-Disciplinary Dataset Discovery from Citation-Verified Literature Contexts

arXiv: https://arxiv.org/abs/2601.05099 · HTML: https://mlsanity.com/paper/2601.05099/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Builds on (most cited first, 15 of 15)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://mlsanity.com/paper/1808.09602/) (2018)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)
- [SciREX: A Challenge Dataset for Document-Level Information Extraction](https://mlsanity.com/paper/2005.00512/) (2020)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [Personalized Generation In Large Model Era: A Survey](https://mlsanity.com/paper/2503.02614/) (2025)
- [SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents](https://mlsanity.com/paper/2410.21155/) (2024)
- [Event-based Stereo Depth Estimation: A Survey](https://mlsanity.com/paper/2409.17680/) (2024)
- [DMDD: A Large-Scale Dataset for Dataset Mentions Detection](https://mlsanity.com/paper/2305.11779/) (2023)
- [A Survey on Patent Analysis: From NLP to Multimodal AI](https://mlsanity.com/paper/2404.08668/) (2024)
- [ChatPD: An LLM-driven Paper-Dataset Networking System](https://mlsanity.com/paper/2505.22349/) (2025)
- [Everything you always wanted to know about a dataset: studies in data summarisation](https://mlsanity.com/paper/1810.12423/) (2018)

## Built on by (most cited first, 4 of 4)

- [Bringing Agentic Search to Earth Observation Data Discovery](https://mlsanity.com/paper/2607.02387/) (2026)
- [Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis](https://mlsanity.com/paper/2602.10881/) (2026)
- [Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP](https://mlsanity.com/paper/2605.17442/) (2026)
- [Large language model-assisted discovery of cohorts from scientific literature](https://mlsanity.com/paper/2608.15909/) (2026)

## Abstract (arXiv)

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).