AINeutralarXiv – CS AI · Feb 276/105
🧠
Decomposing Physician Disagreement in HealthBench
Research analyzing physician disagreement in HealthBench medical AI evaluation dataset finds that 81.8% of disagreement variance is unexplained by observable features, with rubric identity accounting for only 15.8% of variance. The study reveals physicians agree on clearly good or bad AI outputs but disagree on borderline cases, suggesting structural limits to medical AI evaluation consistency.