Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation.

Saved in:
Bibliographic Details
Title: Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation.
Authors: Chen W; Stanford Center for Biomedical Informatics Research, Stanford, CA, USA, wenyuanc@stanford.edu., Haredasht FN; Stanford Center for Biomedical Informatics Research, Stanford, CA, USA, fnateghi@stanford.edu., Black KC; Department of Medicine, Stanford University, Stanford, CA, USA., Grolleau F; Stanford Center for Biomedical Informatics Research, Stanford, CA, USA., Alsentzer E; Department of Biomedical Data Science, Stanford University, Stanford, CA, USA., Chen JH; Stanford Center for Biomedical Informatics Research, Stanford, CA, USA2Department of Medicine, Stanford University, Stanford, CA, USA4Stanford Clinical Excellence Research Center, Stanford University, Stanford, CA, USA., Ma SP; Department of Medicine, Stanford University, Stanford, CA, USA, spma@stanford.edu.
Source: Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing [Pac Symp Biocomput] 2026; Vol. 31, pp. 189-204.
Publication Type: Journal Article
Journal Info: Publisher: World Scientific Country of Publication: United States NLM ID: 9711271 Publication Model: Print Cited Medium: Internet ISSN: 2335-6936 (Electronic) Linking ISSN: 23356928 NLM ISO Abbreviation: Pac Symp Biocomput Subsets: MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:2335-6936
DOI:10.1142/9789819824755_0014