EUVIMEDEUVIMED entdecken
Open Access · CC BY 3.0

SciDaSynth: Interactive Structured Data Extraction From Scientific Literature With Large Language Model

Xingbo Wang iD, Samantha L Huey iD, Rui Sheng, Saurabh Mehta iD, Fei Wang

Campbell Systematic Reviews: Better Evidence for a Better World · 2025-12 · 21 (4)

DOI: 10.1002/cl2.70073 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Campbell Systematic Reviews: Better Evidence for a Better World, online erschienen am 03.11.2025. Verfasst von Xingbo Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Present Address: Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI) Sunnyvale California USA. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0). Gefördert von: NICHD NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The explosion of scientific literature has made the efficient and accurate extraction of structured data a critical component for advancing scientific knowledge and supporting evidence-based decision-making. However, existing tools often struggle to extract and structure multimodal, varied, and inconsistent information across documents into standardized formats. We introduce SciDaSynth, a novel interactive system powered by large language models that automatically generates structured data tables according to users' queries by integrating information from diverse sources, including text, tables, and figures. Furthermore, SciDaSynth supports efficient table data validation and refinement, featuring multi-faceted visual summaries and semantic grouping capabilities to resolve cross-document data inconsistencies. A within-subjects study with nutrition and NLP researchers demonstrates SciDaSynth's effectiveness in producing high-quality structured data more efficiently than baseline methods. We discuss design implications for human–AI collaborative systems supporting data extraction tasks.

Schlagwörter

Stichwörter der Autor:innen

data extractionknowledge baselarge language modelsscientific literature

Autor:innen und Institutionen

  • Present Address: Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI) Sunnyvale California USA.
  • Weill Cornell Medicine Cornell University New York New York USA.
  • Cornell Joan Klein Jacobs Center for Precision Nutrition and Health Cornell University Ithaca New York USA.
  • Hong Kong University of Science and Technology Hong Kong Hong Kong.

ORCID-Profile: Xingbo Wang, Samantha L Huey, Saurabh Mehta

Förderung

  • NICHD NIH HHS

Zitieren

APA

Wang, X., Huey, S. L., Sheng, R., Mehta, S., & Wang, F. (2025). SciDaSynth: Interactive Structured Data Extraction From Scientific Literature With Large Language Model. Campbell Systematic Reviews: Better Evidence for a Better World, 21(4). https://doi.org/10.1002/cl2.70073

Vancouver

Wang X, Huey SL, Sheng R, Mehta S, Wang F. SciDaSynth: Interactive Structured Data Extraction From Scientific Literature With Large Language Model. Campbell Systematic Reviews: Better Evidence for a Better World. 2025;21(4). doi:10.1002/cl2.70073

BibTeX
@article{Wang2025,
  author = {Wang, Xingbo and Huey, Samantha L and Sheng, Rui and Mehta, Saurabh and Wang, Fei},
  title = {SciDaSynth: Interactive Structured Data Extraction From Scientific Literature With Large Language Model},
  journal = {Campbell Systematic Reviews: Better Evidence for a Better World},
  year = {2025},
  volume = {21},
  number = {4},
  doi = {10.1002/cl2.70073}
}
Kostenlos starten →