CVAIFeb 1, 2024

AI-generated faces influence gender stereotypes and racial homogenization

arXiv:2402.01002v335 citationsh-index: 33Sci Rep
AI Analysis

This addresses biases in text-to-image models that affect millions of users, with implications for reducing stereotypes, though it is incremental in proposing debiasing solutions.

The study documented significant racial and gender biases in Stable Diffusion, revealing racial homogenization across professions and attributes, and found that inclusive AI-generated faces reduced biases in a survey experiment.

Text-to-image generative AI models such as Stable Diffusion are used daily by millions worldwide. However, the extent to which these models exhibit racial and gender stereotypes is not yet fully understood. Here, we document significant biases in Stable Diffusion across six races, two genders, 32 professions, and eight attributes. Additionally, we examine the degree to which Stable Diffusion depicts individuals of the same race as being similar to one another. This analysis reveals significant racial homogenization, e.g., depicting nearly all Middle Eastern men as bearded, brown-skinned, and wearing traditional attire. We then propose debiasing solutions that allow users to specify the desired distributions of race and gender when generating images while minimizing racial homogenization. Finally, using a preregistered survey experiment, we find evidence that being presented with inclusive AI-generated faces reduces people's racial and gender biases, while being presented with non-inclusive ones increases such biases, regardless of whether the images are labeled as AI-generated. Taken together, our findings emphasize the need to address biases and stereotypes in text-to-image models.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes