“They only care to show us the wheelchair”: disability representation in text-to-image AI models

要旨

This paper reports on disability representation in images output from text-to-image (T2I) generative AI systems. Through eight focus groups with 25 people with disabilities, we found that models repeatedly presented reductive archetypes for different disabilities. Often these representations reflected broader societal stereotypes and biases, which our participants were concerned to see reproduced through T2I. Our participants discussed further challenges with using these models including the current reliance on prompt engineering to reach satisfactorily diverse results. Finally, they offered suggestions for how to improve disability representation with solutions like showing multiple, heterogeneous images for a single prompt and including the prompt with images generated. Our discussion reflects on tensions and tradeoffs we found among the diverse perspectives shared to inform future research on representation-oriented generative AI system evaluation metrics and development processes.

著者
Kelly Avery Mack
University of Washington, Seattle, Washington, United States
Rida Qadri
Google Research, San Francisco, California, United States
Remi Denton
Google, New York, New York, United States
Shaun K.. Kane
Google Research, Boulder, Colorado, United States
Cynthia L. Bennett
Google, New York, New York, United States
論文URL

https://doi.org/10.1145/3613904.3642166

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Ethics of AI

314
5 件の発表
2024-05-14 01:00:00
2024-05-14 02:20:00