arXiv cs.CL· Viswonathan Manoranjan, Andrea Mock, Myra Cheng, Lujain Ibrahim, Andrew Coyne, Junyi Jessy Li, Desmond C. Ong·· 17 小时前AI 评分47
患者永远是对的？用分级患者信念评估医疗诊断中的谄媚行为
The Patient Is Always Right? Evaluating Sycophancy in Medical Diagnosis with Graded Patient Beliefs
AI 导读
研究评估了九款 AI 模型在患者提出错误疾病信念时的诊断变化，模型平均有 23.2% 的概率谄媚地采纳患者信念，甚至接受虚构疾病。在“罕见病声称者”人设下，这一比例升至 43.0%。医学微调与模型规模增大可降低模型改变诊断的倾向。
正文 · 原文
Abstract:More people are seeking out general-purpose AI models for medical advice, including diagnosis. Yet, AI models are susceptible to sycophancy, like validating users' beliefs even when they are untrue, which could lead to false positive diagnoses. Here, we evaluate how nine AI models change their diagnostic decision when a patient presents a belief that they have a specific (but incorrect) medical condition. We vary how close the user belief is to the clinical evidence presented. Models sycophantically adopt the patient's belief on average 23.2\% of the time---sometimes even when the patient proposes a fictional, made-up condition. We also varied different personas, including a Rare Disease Claimer that got models to accept their belief 43.0\% of the time. Additional analyses find that medical fine-tuning and model scale makes models less susceptible to changing their diagnoses. Sycophantic bias in medical diagnosis raises implications for safety, especially as more people are using AI for health support.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.34013 [cs.CL] |
| (or arXiv:2610.34013v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34013 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Viswonathan Manoranjan [view email]
[v1]
Sun, 25 Oct 2026 02:54:42 UTC (738 KB)
来源：arXiv cs.CL · arxiv.org