@inproceedings{marini-etal-2025-data,
    title = "Data Gatherer: {LLM}-Powered Dataset Reference Extraction from Scientific Literature",
    author = "Marini, Pietro  and
      Santos, A{\'e}cio  and
      Contaxis, Nicole  and
      Freire, Juliana",
    editor = "Ghosal, Tirthankar  and
      Mayr, Philipp  and
      Singh, Amanpreet  and
      Naik, Aakanksha  and
      Rehm, Georg  and
      Freitag, Dayne  and
      Li, Dan  and
      Schimmler, Sonja  and
      De Waard, Anita",
    booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.sdp-1.10/",
    pages = "114--123",
    ISBN = "979-8-89176-265-7",
    abstract = "Despite growing emphasis on data sharing and the proliferation of open datasets, researchers face significant challenges in discovering relevant datasets for reuse and systematically identifying dataset references within scientific literature. We present Data Gatherer, an automated system that leverages large language models to identify and extract dataset references from scientific publications. To evaluate our approach, we developed and curated two high-quality benchmark datasets specifically designed for dataset identification tasks. Our experimental evaluation demonstrates that Data Gatherer achieves high precision and recall in automated dataset reference extraction, reducing the time and effort required for dataset discovery while improving the systematic identification of data sources in scholarly literature."
}