@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://aclanthology.org/2025.sdp-1.10/",
doi = "10.18653/v1/2025.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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marini-etal-2025-data">
<titleInfo>
<title>Data Gatherer: LLM-Powered Dataset Reference Extraction from Scientific Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pietro</namePart>
<namePart type="family">Marini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aécio</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicole</namePart>
<namePart type="family">Contaxis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juliana</namePart>
<namePart type="family">Freire</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanpreet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">De Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-265-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">marini-etal-2025-data</identifier>
<identifier type="doi">10.18653/v1/2025.sdp-1.10</identifier>
<location>
<url>https://aclanthology.org/2025.sdp-1.10/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>114</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Gatherer: LLM-Powered Dataset Reference Extraction from Scientific Literature
%A Marini, Pietro
%A Santos, Aécio
%A Contaxis, Nicole
%A Freire, Juliana
%Y Ghosal, Tirthankar
%Y Mayr, Philipp
%Y Singh, Amanpreet
%Y Naik, Aakanksha
%Y Rehm, Georg
%Y Freitag, Dayne
%Y Li, Dan
%Y Schimmler, Sonja
%Y De Waard, Anita
%S Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-265-7
%F marini-etal-2025-data
%X 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.
%R 10.18653/v1/2025.sdp-1.10
%U https://aclanthology.org/2025.sdp-1.10/
%U https://doi.org/10.18653/v1/2025.sdp-1.10
%P 114-123
Markdown (Informal)
[Data Gatherer: LLM-Powered Dataset Reference Extraction from Scientific Literature](https://aclanthology.org/2025.sdp-1.10/) (Marini et al., sdp 2025)
ACL