Poster
in
Affinity Event: Women in Machine Learning

Bias Assessment of Text-to-Image Models

Sasha Alexandra Luccioni ⋅ Clémentine Fourrier ⋅ Nathan Lambert ⋅ Unso Eun Seo Jo ⋅ Irene Solaiman ⋅ Helen Ngo ⋅ Nazneen Rajani ⋅ Giada Pistilli ⋅ Yacine Jernite ⋅ Margaret Mitchell

[ Poster]

Abstract

While Text-to-Image models such as Dall-E and Stable Diffusion are becoming increasingly adept at creating new content, they also open doors to new types of harms and biases. We describe some of the challenges raised by deploying these models, provide a case study for bias assessment, and discuss future avenues of exploration in the field.

Chat is not available.