Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913811619905536 |
|---|---|
| author | Aman, Tabinda Nadeem, Mohammad Sohail, Shahab Saquib Anas, Mohammad Cambria, Erik |
| author_facet | Aman, Tabinda Nadeem, Mohammad Sohail, Shahab Saquib Anas, Mohammad Cambria, Erik |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12433 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models Aman, Tabinda Nadeem, Mohammad Sohail, Shahab Saquib Anas, Mohammad Cambria, Erik Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language 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. |
| title | Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2501.12433 |