T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Models

TL;DR

This paper investigates societal biases encoded in the latent spaces of popular text-to-image models, revealing gender and race stereotypes in generated images and proposing strategies for bias mitigation.

Contribution

It provides an empirical analysis of societal biases in five leading T2I models, highlighting specific patterns and offering insights for responsible AI deployment.

Findings

All models encode gender stereotypes in profession representations.

Models show racial biases, with some focusing on specific ethnic groups.

Bias mitigation strategies are discussed for responsible AI development.

Abstract

Text-to-image (T2I) generative models are largely used in AI-powered real-world applications and value creation. However, their strategic deployment raises critical concerns for responsible AI management, particularly regarding the reproduction and amplification of race- and gender-related stereotypes that can undermine organizational ethics. In this work, we investigate whether such societal biases are systematically encoded within the pretrained latent spaces of state-of-the-art T2I models. We conduct an empirical study across the five most popular open-source models, using ten neutral, profession-related prompts to generate 100 images per profession, resulting in a dataset of 5,000 images evaluated by diverse human assessors representing different races and genders. We demonstrate that all five models encode and amplify pronounced societal skew: caregiving and nursing roles are consistently feminized, while high-status professions such as corporate CEO, politician, doctor, and lawyer are overwhelmingly represented by males and mostly White individuals. We further identify model-specific patterns, such as QWEN-Image's near-exclusive focus on East Asian outputs, Kandinsky's dominance of White individuals, and SDXL's comparatively broader but still biased distributions. These results provide critical insights for AI project managers and practitioners, enabling them to select equitable AI models and customized prompts that generate images in alignment with the principles of responsible AI. We conclude by discussing the risks of these biases and proposing actionable strategies for bias mitigation in building responsible GenAI systems. The code and Data Repository: https://github.com/Sufianlab/T2IBias