发现视觉语言模型会延续猫头鹰聪明、狐狸狡诈等动物刻板印象。
Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models
- 用特定提示词测试DALL-E生成图像，观察文化偏见如何被模型复制。
- 模型反复生成符合人类文化偏见的动物形象，如狐狸常被画成背叛者。
- 首次系统揭示AI图像生成中的动物刻板印象，适合关注AI伦理的研究者。
动物刻板印象深深植根于人类文化和语言中，常影响我们对不同物种的感知与期待。本研究调查了在图像生成任务中，视觉语言模型如何体现动物刻板印象。通过针对性提示词，我们探究DALL-E是否延续诸如“猫头鹰代表智慧”“狐狸代表不忠”等文化偏见。研究发现，模型显著生成与文化偏见一致的图像，呈现系统性刻板现象。这是首个系统性考察视觉语言模型中动物刻板印象的研究，揭示了人工智能生成视觉内容中一个关键但未被充分关注的偏见维度。
原文摘要 · Abstract (English)
Animal stereotypes are deeply embedded in human culture and language. They often shape our perceptions and expectations of various species. Our study investigates how animal stereotypes manifest in vision-language models during the task of image generation. Through targeted prompts, we explore whether DALL-E perpetuates stereotypical representations of animals, such as "owls as wise," "foxes as unfaithful," etc. Our findings reveal significant stereotyped instances where the model consistently generates images aligned with cultural biases. The current work is the first of its kind to examine animal stereotyping in vision-language models systematically and to highlight a critical yet underexplored dimension of bias in AI-generated visual content.
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。