arXiv cs.CY· Mengting Wei, Aditya Gulati, Guoying Zhao, Nuria Oliver·· 12 小时前AI 评分37
情感提示词如何加剧 T2I 人脸生成的群体偏见：八款中西模型审计
Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generation
AI 导读
一项审计对 8 款 T2I 模型（4 款西方、4 款中国）在 7 种提示条件下生成 56,000 张人脸，发现所有模型都严重过度呈现年轻面孔，多数还过度呈现 White-coded 个体。负面情绪提示词（如悲伤、恐惧）会稳定地把输出推向 White、中年、男性编码面孔，并伴随更低的可感知吸引力。年轻×女性×Black 等交叉组合在多数模型中近乎消失，单属性审计无法捕捉这类复合缺失。
正文 · 原文
Abstract:Synthetic faces from text-to-image (T2I) models pervade digital media, yet their demographic biases under emotionally conditioned prompts remain poorly understood. We aim to systematically audit how emotionally conditioned prompts affect demographic and perceived-attractiveness biases in synthetic faces generated by T2I models, with particular attention to intersectional patterns and cross-ecosystem differences across model families. We audited eight (4 Western and 4 Chinese) T2I models and generated 56,000 faces under seven prompt conditions: a neutral baseline and six emotion conditions. We quantified biases in gender, race, age, and perceived attractiveness using information-theoretic divergence metrics. We further conducted intersectional analyses across combined demographic attributes and compared patterns between the Western and Chinese model groups to assess cross-ecosystem consistency and divergence in bias behavior. All models show strong overrepresentation of young faces, and most also overrepresent White-coded individuals. Intersectional analysis reveals compound underrepresentation or near-erasure of specific demographic combinations, such as young x female x Black faces, which are largely absent across models and are not captured by single-attribute audits. Emotion prompts act as additional demographic selectors: negatively valenced emotions (including sadness and fear) consistently shift outputs toward White, middle-aged, male-coded faces. This produces a valence-driven mapping that is also associated with lower perceived attractiveness in generated faces. These findings indicate that demographic bias in T2I face generation is both pervasive and shaped by emotional conditioning. They underscore the need for intersectional, emotion-conditioned, and multilingual demographic audits as part of standard pre-deployment evaluation practices.
| Comments: | 45 pages, 18 figures, 27 tables |
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2602.00032 [cs.CY] |
| (or arXiv:2602.00032v4 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2602.00032 arXiv-issued DOI via DataCite |
Submission history
From: Aditya Gulati [view email]
[v1]
Sun, 18 Jan 2026 13:35:51 UTC (4,463 KB)
[v2]
Tue, 3 Feb 2026 08:10:05 UTC (4,463 KB)
[v3]
Mon, 22 Jun 2026 15:21:09 UTC (12,389 KB)
[v4]
Fri, 16 Oct 2026 13:54:34 UTC (12,707 KB)
来源：arXiv cs.CY · arxiv.org