2 papers
cs.CL2025
Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation
Wenyuan Chen, Fateme Nateghi Haredasht, Kameron C. Black +4
Asynchronous patient-clinician messaging via EHR portals is a growing source of clinician workload, prompting interest in large language models (LLMs) to assist with draft response…
stat.ME2025
powerROC: An Interactive Web Tool for Sample Size Calculation in Assessing Models' Discriminative Abilities
François Grolleau, Robert Tibshirani, Jonathan H. Chen
Rigorous external validation is crucial for assessing the generalizability of prediction models, particularly by evaluating their discrimination (AUROC) on new data. This often inv…