Clinician use of language models diverges from how the models are evaluated
Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their readiness rest largely on benchmark scores, most of them derived from examination questions or curated cases. A benchmark predicts performance in deployment only to the extent that its items resemble...
K. Vishwanath, Hai-Tong Lin, A. Alyakin et al.
· 0 citations