Imagen de Portada

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

Guardado en:
Publicado en:Campbell Systematic Reviews vol. 21, no. 4 (Dec 1, 2025)
Autor principal: Wang, Xingbo
Otros Autores: Huey, Samantha L., Sheng, Rui, Mehta, Saurabh, Wang, Fei
Publicado:
John Wiley & Sons, Inc.
Materias:
World Health Organization
Accuracy
Extraction
Models
Novels
Nutrition
Adaptation
Data quality
Documents
COVID-19
Natural language
Semantics
Materials science
Decision making
Literary criticism
Scientific knowledge
Flexibility
Medical research
Researcher subject relations
Data
Language modeling
Large language models
Tables (Data)
Prompting
Researchers
Meta Analysis
Comprehension
Information Needs
Reference Materials
Natural Language Processing
Scientific Research
Information Seeking
Artificial Intelligence
Evidence Based Practice
Science Materials
Language Processing
Algorithms
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:ABSTRACT 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.
ISSN:1891-1803
DOI:10.1002/cl2.70073
Fuente:Sociology Database