arXiv cs.CY· Matilde Elene Hansen, Ross Deans Kristensen-McLachlan·· 12 小时前AI 评分31
GPT-4o 在 ADHD 自我诊断中的性别关联研究
Gender Associations in LLM-Mediated ADHD Self-Diagnosis
AI 导读
研究将 Context Association Test（CAT）适配到零样本自我诊断场景，评估 GPT-4o 是否响应 ADHD 的性别化关联。显式性别提示会持续放大特定 ADHD 亚型关联，而隐式提示产生的分布接近代理基线。作者认为显式人口学提示可能激活过度纠正的偏见缓解机制，而非真正消除偏见。
正文
Abstract:Large Language Models (LLMs) are increasingly used for medical self-diagnosis. However, the way demographic cues shape outputs in these interactions remains poorly understood. This is particularly consequential for diagnoses like ADHD, where persistent gender disparities are not fully aligned with the clinical evidence. We adapt the Context Association Test (CAT) to evaluate whether GPT-4o responds to gendered ADHD associations in a zero-shot, self-diagnostic setting. We show that explicit cueing consistently amplifies certain ADHD subtype associations while implicit cueing produces near proxy-aligned distributions. These divergences suggest that explicit demographic cues may activate bias-mitigation mechanisms that over-correct rather than eliminate bias, whereas implicit cues appear to reflect the model's default behavior. Our results demonstrate that evaluating gendered bias in LLM-mediated self-diagnosis requires careful attention to the demographic associations a model encodes.
| Comments: | 20 pages (10 pages of main text, plus references and appendix). Accepted at EVAL4SD 2026. To appear in the ACL Anthology |
| Subjects: | Computation and Language (cs.CL); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.33697 [cs.CL] |
| (or arXiv:2610.33697v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33697 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Matilde Elene Hansen [view email]
[v1]
Sat, 24 Oct 2026 14:24:11 UTC (266 KB)
来源：arXiv cs.CY · arxiv.org