Scholarlink

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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Owls are Wise and Foxes are Unfaithful: Uncovering Animal Stereotypes in Vision Language Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Tabinda Aman,
  • Mohammad Nadeem,
  • Shahab Saquib Sohail,
  • Mohammad Anas,
  • Erik Cambria

摘要

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.