Back to Search Start Over

Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets

Authors :
Ghosh, Satanu
Brodnik, Neal R.
Frey, Carolina
Holgate, Collin
Pollock, Tresa M.
Daly, Samantha
Carton, Samuel
Publication Year :
2024

Abstract

We explore the ability of GPT-4 to perform ad-hoc schema based information extraction from scientific literature. We assess specifically whether it can, with a basic prompting approach, replicate two existing material science datasets, given the manuscripts from which they were originally manually extracted. We employ materials scientists to perform a detailed manual error analysis to assess where the model struggles to faithfully extract the desired information, and draw on their insights to suggest research directions to address this broadly important task.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2406.05348
Document Type :
Working Paper