AI图像模型显示出人口统计学偏见，新研究发现 · 跟踪4个来源

报道来源 [4]

1. arXiv cs.AI TIER_1 English(EN) · Dasol Choi, Jihwan Lee, Minjae Lee, Minsuk Kahng · 2026-06-18 04:00

   当汽车有了刻板印象：文本到图像模型中对象的人口统计偏见审计

   arXiv:2508.03483v3 Announce Type: replace-cross Abstract: While prior research on text-to-image generation has predominantly focused on biases in human depictions, demographic bias in generated objects remains relatively underexplored. We introduce SODA (Stereotyped Object Diagno…

2. arXiv cs.LG TIER_1 English(EN) · NaHyeon Park, Na Min An, Kunhee Kim, Soyeon Yoon, Jiahao Huo, Hyunjung Shim · 2026-06-15 04:00

   对齐但刻板印象？系统提示如何塑造 LLM 文本到图像模型中的人口统计偏见

   arXiv:2512.04981v2 Announce Type: replace-cross Abstract: Text-to-image (T2I) systems increasingly rely on Large Language Model (LLM)-based text conditioning to interpret and expand user prompts. While this improves prompt understanding and text-image alignment, we find that it c…

3. arXiv cs.CV TIER_1 English(EN) · Thomas Klassert, Adrian Ulges, Biying Fu · 2026-06-19 04:00

   BAFIS：用于评估现代文本到图像模型中职业偏见和人类偏好的数据集+框架

   arXiv:2606.20241v1 Announce Type: new Abstract: Generative artificial intelligence has the potential to improve productivity and transform the production of creative content. However, existing research indicates that image generation models are significantly influenced by biases.…

4. arXiv cs.CV TIER_1 English(EN) · Biying Fu · 2026-06-18 13:52

   BAFIS：用于评估现代文本到图像模型中职业偏见和人类偏好的数据集+框架

   Generative artificial intelligence has the potential to improve productivity and transform the production of creative content. However, existing research indicates that image generation models are significantly influenced by biases. This work investigates the inherent biases and …