Imagining the Far East: Exploring Perceived Biases in AI-Generated Images of East Asian Women
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917979145371648 |
|---|---|
| author | Lan, Xingyu An, Jiaxi Guo, Yisu Tong, Chiyou Cai, Xintong Zhang, Jun |
| author_facet | Lan, Xingyu An, Jiaxi Guo, Yisu Tong, Chiyou Cai, Xintong Zhang, Jun |
| contents | Image-generating AI, which allows users to create images from text, is increasingly used to produce visual content. Despite its advancements, cultural biases in AI-generated images have raised significant concerns. While much research has focused on issues within Western contexts, our study examines the perceived biases regarding the portrayal of East Asian women. In this exploratory study, we invited East Asian users to audit three popular models (DALL-E, Midjourney, Stable Diffusion) and identified 18 specific perceived biases, categorized into four patterns: Westernization, overuse or misuse of cultural symbols, sexualization & feminization, and racial stereotypes. This work highlights the potential challenges posed by AI models in portraying Eastern individuals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04865 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Imagining the Far East: Exploring Perceived Biases in AI-Generated Images of East Asian Women Lan, Xingyu An, Jiaxi Guo, Yisu Tong, Chiyou Cai, Xintong Zhang, Jun Human-Computer Interaction Image-generating AI, which allows users to create images from text, is increasingly used to produce visual content. Despite its advancements, cultural biases in AI-generated images have raised significant concerns. While much research has focused on issues within Western contexts, our study examines the perceived biases regarding the portrayal of East Asian women. In this exploratory study, we invited East Asian users to audit three popular models (DALL-E, Midjourney, Stable Diffusion) and identified 18 specific perceived biases, categorized into four patterns: Westernization, overuse or misuse of cultural symbols, sexualization & feminization, and racial stereotypes. This work highlights the potential challenges posed by AI models in portraying Eastern individuals. |
| title | Imagining the Far East: Exploring Perceived Biases in AI-Generated Images of East Asian Women |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2504.04865 |