Resources


Database Credentialed Access

MIMIC-III-Ext-VeriFact-BHC: Labeled Propositions From Brief Hospital Course Summaries for Long-form Clinical Text Evaluation

Philip Chung, Akshay Swaminathan, Alex Goodell, et al.

A clinician-labeled dataset for fact-checking long-form clinical text against patient EHRs. The dataset contains LLM-written and human-written Brief Hospital Course summaries decomposed to atomic claim and sentence propositions with annotations.

natural language processing clinical notes electronic health records brief hospital course large language models long-form text chart review text reranking atomic claim hybrid retrieval clinical informatics clinical medicine fact verification retrieval-augmented generation logical atomism text embedding formal logic llm-as-a-judge llm evaluation artificial intelligence

Published: April 9, 2025. Version: 1.0.0