RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs
RegExtract is introduced, a benchmark for structured information extraction from PFAS regulatory documents, comprising 488 human-annotated field instances across 20 US state documents and 46 regulations, and a typed, multi-field schema targeting key elements such as material definitions, permitted uses, and product exe...
Defne Çirci, Krystelle Lionti, Sarathkrishna Swaminathan et al.
· 0 citations