测试不同语言描述对AI生成职业图像性别偏见的影响
Effect of Gender Fair Job Description on Generative AI Images
- 用德语通用阳性、德语成对形式和英语三种表述生成图像
- 所有形式均显示男性主导，德语成对形式偏见减轻但未消除
- 适合关注AI伦理与性别公平的研究者阅读
STEM领域传统上以男性为主，性别偏见影响职业可及性认知。本研究分析了使用OpenAI DALL-E 3与Black Forest FLUX.1，基于150个提示词在三种语言形式（德语通用阳性、德语成对形式、英语）下生成的STEM职业图像中的性别表现。作为对照，还生成了20张社会职业图像。结果显示，所有语言形式均存在显著男性偏见，德语成对形式虽减少偏见，但在STEM群体中仍过度呈现男性，社会职业组则结果不一。研究还分析了年龄分布与种族多样性。结果凸显生成式AI强化社会偏见的风险，强调需进一步讨论人工智能中的多样性问题。
原文摘要 · Abstract (English)
STEM fields are traditionally male-dominated, with gender biases shaping perceptions of job accessibility. This study analyzed gender representation in STEM occupation images generated by OpenAI DALL-E 3 \& Black Forest FLUX.1 using 150 prompts in three linguistic forms: German generic masculine, German pair form, and English. As control, 20 pictures of social occupations were generated as well. Results revealed significant male bias across all forms, with the German pair form showing reduced bias but still overrepresenting men for the STEM-Group and mixed results for the Group of Social Occupations. These findings highlight generative AI's role in reinforcing societal biases, emphasizing the need for further discussion on diversity (in AI). Further aspects analyzed are age-distribution and ethnic diversity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。