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

• URL: http://arxiv.org/abs/2604.16516v1
• Date: Wed, 15 Apr 2026 11:11:39 GMT
• Title: Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies
• Abstract summary: Text-to-Image (T2I) generation models have been widely adopted across various industries, yet are criticized for frequently exhibiting societal stereotypes.<n>This paper provides a comprehensive systematic review of T2I fairness literature, organizing existing work into a taxonomy of bias types and fairness notions.<n>We propose a new framework for operationalizing fairness that moves beyond descriptive metrics towards rigorous, target-based testing.
• Score: 5.336565378315399
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Position: Fairness Failure in Generative Models is an Evaluation Problem [5.939858158928473]
  This paper argues that fairness failures in generative models are ultimately stemming from an evaluation problem.<n>We propose Fairness Cards as a minimal reporting artifact that makes evaluation choices explicit.
  arXiv  Detail & Related papers  (2026-08-17T14:41:28Z)
• HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing [20.795940054868854]
  Existing evaluation methods address only single-dimensional biases.<n>We introduce HoloFair, a comprehensive benchmark framework for multidimensional demographic bias analysis.<n>We also introduce Fair-GRPO, a reinforcement-learning-based debiasing method.
  arXiv  Detail & Related papers  (2026-05-23T17:52:07Z)
• BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models [30.463069540851688]
  We introduce BiasIG, a unified benchmark that quantifies social biases across a curated dataset of 47,040 prompts.<n>Extensive experiments on 8 T2I models and 3 debiasing methods validate BiasIG as a robust diagnostic tool.<n>Our work advocates for a precise, taxonomy-driven approach to fairness in AIGC, providing a theoretical framework for using BiasIG's metrics as feedback signals in future closed-loop mitigation.
  arXiv  Detail & Related papers  (2026-04-13T18:22:50Z)
• Intersectional Fairness via Mixed-Integer Optimization [2.664154603948153]
  We argue that true fairness requires addressing bias at the intersections of protected groups.<n>We propose a unified framework that leverages Mixed-Integer Optimization (MIO) to train intersectionally fair and intrinsically interpretable classifiers.
  arXiv  Detail & Related papers  (2026-01-27T13:29:25Z)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models [0.0]
  Text-to-Image (TTI) systems have come under increased scrutiny for social biases. We investigate embedding spaces as a source of bias for TTI models. We find that biased multimodal embeddings like CLIP can result in lower alignment scores for representationally balanced TTI models.
  arXiv  Detail & Related papers  (2024-09-15T01:09:55Z)
• Identifying and Mitigating Social Bias Knowledge in Language Models [52.52955281662332]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.<n>FAST surpasses state-of-the-art baselines with superior debiasing performance.<n>This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Quantifying Bias in Text-to-Image Generative Models [49.60774626839712]
  Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas. Existing T2I model bias evaluation methods only focus on social biases. We propose an evaluation methodology to quantify general biases in T2I generative models, without any preconceived notions.
  arXiv  Detail & Related papers  (2023-12-20T14:26:54Z)
• DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision [73.80009454050858]
  This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Our model jointly optimize for two fairness criteria - group fairness and counterfactual fairness.
  arXiv  Detail & Related papers  (2023-03-15T07:13:54Z)
• Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP [64.45845091719002]
  Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. This paper seeks to clarify the current situation and plot a course for meaningful progress in fair learning.
  arXiv  Detail & Related papers  (2023-02-11T14:54:00Z)
• Optimising Equal Opportunity Fairness in Model Training [60.0947291284978]
  Existing debiasing methods, such as adversarial training and removing protected information from representations, have been shown to reduce bias. We propose two novel training objectives which directly optimise for the widely-used criterion of it equal opportunity, and show that they are effective in reducing bias while maintaining high performance over two classification tasks.
  arXiv  Detail & Related papers  (2022-05-05T01:57:58Z)
• The Long Arc of Fairness: Formalisations and Ethical Discourse [0.0]
  We argue that the relations between technical (formalised) and ethical discourse on fairness are not always clear and productive. We introduce dynamic fairness modelling, a more comprehensive approach that realigns formal fairness metrics with arguments from the ethical discourse. By contextualising these elements of fairness-related processes, dynamic fairness modelling explicates formerly latent ethical aspects.
  arXiv  Detail & Related papers  (2022-03-08T09:54:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.