Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models

TL;DR

This study investigates how vision-language models like DALL-E reproduce animal stereotypes from human culture, revealing significant biases in generated images through targeted prompts, and is the first systematic examination of this issue.

Contribution

It introduces the first systematic analysis of animal stereotypes in vision-language models, highlighting cultural biases in AI-generated images.

Findings

Models often generate stereotypical images based on prompts.

Significant bias towards cultural stereotypes in generated content.

Highlights need for bias mitigation in vision-language models.

Abstract

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.