Papers by Jane Warren
Decoding Fatphobia: Examining Anti-Fat and Pro-Thin Bias in AI-Generated Images (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have shown that AI-generated images reinforce social biases, including those related to race and gender. |
| Approach: | They use DALL-E 3 to examine weight bias in AI-generated images . authors discuss findings and their impact on existing research on weight bias . |
| Outcome: | The study examines stereotypical associations between moral character and body weight . it finds that fatphobia is a feature of social systems that rank fatter bodies inferior to thinner bodies . |