Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies

2026-04-15

AI Summary

Text-to-image (T2I) generative models commonly exhibit social stereotypes, yet the lack of operational definitions for “bias” and “fairness” hinders effective evaluation and mitigation. This study addresses this gap through a systematic literature review, establishing a taxonomy of bias types and fairness concepts in T2I generation, and clarifying the distinction between target fairness and threshold fairness. It further evaluates a range of mitigation strategies—from prompt engineering to interventions in the diffusion process—and proposes an actionable fairness framework. By shifting the evaluation paradigm from descriptive metrics toward goal-oriented, rigorous testing, this work constructs a structured knowledge base for T2I fairness research, offering both theoretical grounding and practical pathways for the responsible development of generative AI systems.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Ethics, Bias, and Fairness
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Text-to-Image (T2I) generation models have been widely adopted across various industries, yet are criticized for frequently exhibiting societal stereotypes. While a growing body of research has emerged to evaluate and mitigate these biases, the field at present contends with conceptual ambiguity, for example terms like "bias" and "fairness" are not always clearly distinguished and often lack clear operational definitions. This paper provides a comprehensive systematic review of T2I fairness literature, organizing existing work into a taxonomy of bias types and fairness notions. We critically assess the gap between "target fairness" (normative ideals in T2I outputs) and "threshold fairness" (normative standards with actionable decision rules). Furthermore, we survey the landscape of mitigation strategies, ranging from prompt engineering to diffusion process manipulation. We conclude by proposing a new framework for operationalizing fairness that moves beyond descriptive metrics towards rigorous, target-based testing, offering an approach for more accountable generative AI development.

Problem

• bias
• fairness
• text-to-image models
• operationalization
• stereotypes

Innovation

• fairness operationalization
• text-to-image generation
• bias taxonomy
• target fairness
• generative AI accountability