LLM clinical ethics audit: near-deterministic decisions underweight patient autonomy
zakkohane · x · 2026-11-12
An arXiv paper, What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models, presents a framework for auditing value pluralism in medical AI, with a benchmark of clinician-verified ethical dilemmas and an attribution method that recovers value priorities from decisions. Key findings: frontier models span physician-level value heterogeneity and discuss competing values in reasoning (Overton pluralism), yet individual model decisions are near-deterministic across repeated sampling and semantic variations, failing to reproduce the distributional pluralism of physician panels. Most priorities fall within natural inter-physician variation, but some models significantly underweight patient autonomy. Zak Kohane ties this to the case for AI pluralism; results to be presented at NeurIPS.
More from Safety
- Dev complains security features are gated behind expensive enterprise plans — AccBalanced · 2026-11-12
- SAFE-SEARCH workshop at ECIR 2027 calls for papers on safe conversational search — HamedZamani · 2026-11-12
- Toby Ord argues predeployment testing misses the real risk: internal frontier models — ben_j_todd · 2026-11-12
- The biggest AI control risks come from internal models, not public releases — ben_j_todd · 2026-11-12
- Data centers power 20% of US tech sector and half of decade's stock gains — SydSteyerhart · 2026-11-12
- Scale AI paper: 36% of 374 attack runs succeed — frontier models can covertly sabotage their successors — Miles_Brundage · 2026-11-12