Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917417618243584 |
|---|---|
| author | Smith, Megan Sambandham, Venkatesh Thirugnana Richter, Florian Crompton, Laura Uhl, Matthias Schön, Torsten |
| author_facet | Smith, Megan Sambandham, Venkatesh Thirugnana Richter, Florian Crompton, Laura Uhl, Matthias Schön, Torsten |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16516 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies Smith, Megan Sambandham, Venkatesh Thirugnana Richter, Florian Crompton, Laura Uhl, Matthias Schön, Torsten Computer Vision and Pattern Recognition Machine Learning Multimedia 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. |
| title | Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies |
| topic | Computer Vision and Pattern Recognition Machine Learning Multimedia |
| url | https://arxiv.org/abs/2604.16516 |