Safety and accuracy diverge across deployment conditions in clinical large language models

The study introduces Safety-Focused Evaluation of Scaling (SaFE-Scale) and applies it to RadSaFE-200, a 200-question radiology benchmark with clinician-defined evidence and safety labels. Thirty-four local large language models were tested under six deployment conditions, showing that providing clean clinician-written evidence significantly improved accuracy and reduced high-risk errors and dangerous overconfidence. The results indicate that safety in clinical LLMs depends more on deployment choices than on model size or inference-time compute.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• rag
• agents
• benchmarks
• safety