aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score60

Study finds self-preference in medical LLM evaluationMachine translation

AI introduction

A Stanford paper tested eight models from OpenAI, Anthropic, Google and Qwen on 620 real clinician questions, then had them rank the anonymized answers. Every model ranked its own answer higher than the other judges did, by 1.22 positions on average; revealing model names reduced the bias by only 0.094 positions.

Original post · Original

@rohanpaul_ai

– https://t.co/rcuhEy3o0D

Title: "The Judge Is Not Impartial: Self-Preference in Medical LLM Evaluation"

ReplyRohan Paul@rohanpaul_ai
New Stanford paper finds that all 8 LLMs tested rank their own medical answers higher than other models rank them, even when answers are anonymous. Medical AI benchmarks often use LLMs to grade other LLMs' answers. If a judge favors its own outputs, the benchmark tilts toward that model. They had 8 models from OpenAI, Anthropic, Google and Qwen answer 620 real clinician questions, then rank all 8 anonymous answers. They compared where each judge placed its own answer with where the other 7 judges placed that same answer. Every judge favored its own answer, by 1.22 rank positions on average and nearly 3 for GPT-5.6 Sol. The bias held without a rubric, and revealing model names cut it by only 0.094 positions. If you use LLM judges, use a panel from several model families and report results per judge instead of 1 pooled score.
View this post on X ↗

Source: Rohan Paul · x.com

Research
Found an error? Send a correction