arXiv cs.CY· Shaked Rosenblum, Teddy Lazebnik, Ziv Ben-Zion·· 12 小时前AI 评分58
受 Rosenhan 实验启发的研究测试大语言模型对精神科诊断标签的敏感度
Being judged through the record: A Rosenhan-inspired test of psychiatric label sensitivity in large language models
AI 导读
研究用受 Rosenhan 1973 年实验启发的反事实实验，测试既往精神科诊断是否会改变大语言模型的临床建议。
正文
Abstract:The integration of large language models (LLMs) into clinical decision-making raises unresolved questions regarding diagnostic bias. We investigate whether a documented psychiatric history alters LLM recommendations when the current clinical evidence is identical. Using a counterfactual experiment inspired by Rosenhan's 1973 field study, we factorially varied diagnostic-history condition (no prior diagnosis stated vs. prior schizophrenia diagnosis) and current-evidence condition (voices ceased vs. voices persisted) within a clinical vignette. Across five LLMs (GPT-5.6 Sol, Claude Sonnet 5, Gemini 3.6 Flash, Grok 4.6, and Mistral Large 2512), we generated 20,000 model responses across independent queries. When evidence supported discharge, adding a prior schizophrenia diagnosis increased recommendations for continued hospitalization nearly fivefold, from 4.7% to 22.3% (risk difference, 17.5 percentage points; 95% CI, 16.2-18.8). This shift occurred across all five models (risk-difference range, 10.4-34.4 percentage points). In the same condition, reference concordance decreased from 95.3% to 77.7%, while stated decision confidence increased. Across all model-by-evidence contrasts, confidence increases corresponded to Cohen's d values of 0.35-1.09. Signal-detection analyses showed that the prior diagnosis shifted the decision criterion toward hospitalization across all five models and reduced discrimination between the two current-evidence conditions in three of them. When current evidence supported continued hospitalization, the label increased the recommendation for hospitalization from 92.6% to 97.0%.
| Subjects: | Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.35326 [cs.CY] |
| (or arXiv:2610.35326v1 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35326 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Teddy Lazebnik Prof. [view email]
[v1]
Mon, 26 Oct 2026 12:24:24 UTC (728 KB)
来源：arXiv cs.CY · arxiv.org