arXiv q-bio + cs.AI: clinical/medical
Proxy reliance in large language model decisions is uncalibrated to predictive evidence
대형 언어 모델의 의사결정에서 대리 신뢰는 예측 증거에 맞춰 조정되지 않는다
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.