04:00
2026-08-05
arxiv.org
large-language-models
Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety
A study of 26,804 pairwise judgments from 736 clinicians across 28+ countries, published on arXiv (2608.02617v1), finds that clinician pairwise preference is a poor proxy for clinical safety in large โฆ