Content area
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.
Details
; Huey, Samantha L. 2
; Sheng, Rui 3 ; Mehta, Saurabh 4
; Wang, Fei 4 1 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
2 Cornell Joan Klein Jacobs Center for Precision Nutrition and Health, Cornell University, Ithaca, New York, USA
3 Hong Kong University of Science and Technology, Hong Kong, Hong Kong
4 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