A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models
This study addresses social bias issues in AI for users and developers of image generation technology, but it is incremental as it extends prior research on occupational biases to daily activities.
The paper tackles the problem of gender bias in text-to-image generative models by conducting a large-scale analysis of 2,293,295 images generated from 3,217 gender-neutral prompts across five models, finding that these models reinforce traditional gender roles, such as portraying women predominantly in care scenarios and men in technical or physical labor scenarios.
With the increasing use of image generation technology, understanding its social biases, including gender bias, is essential. This paper presents a large-scale study on gender bias in text-to-image (T2I) models, focusing on everyday situations. While previous research has examined biases in occupations, we extend this analysis to gender associations in daily activities, objects, and contexts. We create a dataset of 3,217 gender-neutral prompts and generate 200 images over 5 prompt variations per prompt from five leading T2I models. We automatically detect the perceived gender of people in the generated images and filter out images with no person or multiple people of different genders, leaving 2,293,295 images. To enable a broad analysis of gender bias in T2I models, we group prompts into semantically similar concepts and calculate the proportion of male- and female-gendered images for each prompt. Our analysis shows that T2I models reinforce traditional gender roles and reflect common gender stereotypes in household roles. Women are predominantly portrayed in care and human-centered scenarios, and men in technical or physical labor scenarios.