# Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models

arXiv: https://arxiv.org/abs/2505.17280 · HTML: https://mlsanity.com/paper/2505.17280/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 30 of 31)

- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models](https://mlsanity.com/paper/2102.04130/) (2021)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [Assessing Social and Intersectional Biases in Contextualized Word Representations](https://mlsanity.com/paper/1911.01485/) (2019)
- [An Intersectional Definition of Fairness](https://mlsanity.com/paper/1807.08362/) (2018)
- [Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion](https://mlsanity.com/paper/2310.03502/) (2023)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [Mitigating Language-Dependent Ethnic Bias in BERT](https://mlsanity.com/paper/2109.05704/) (2021)
- [Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation](https://mlsanity.com/paper/2205.04610/) (2022)
- [SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2312.00825/) (2023)
- [TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.01261/) (2023)
- [Characterizing Intersectional Group Fairness with Worst-Case Comparisons](https://mlsanity.com/paper/2101.01673/) (2021)
- [Gender and Racial Bias in Visual Question Answering Datasets](https://mlsanity.com/paper/2205.08148/) (2022)
- [Assessing Multilingual Fairness in Pre-trained Multimodal Representations](https://mlsanity.com/paper/2106.06683/) (2021)
- [Mitigating stereotypical biases in text to image generative systems](https://mlsanity.com/paper/2310.06904/) (2023)
- [Fair SA: Sensitivity Analysis for Fairness in Face Recognition](https://mlsanity.com/paper/2202.03586/) (2022)

## Built on by (most cited first, 2 of 2)

- [Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems](https://mlsanity.com/paper/2508.12026/) (2025)
- [Measures of classification bias derived from sample size analysis](https://mlsanity.com/paper/2601.03453/) (2026)

## Abstract (arXiv)

The biases exhibited by text-to-image (TTI) models are often treated as independent, though in reality, they may be deeply interrelated. Addressing bias along one dimension - such as ethnicity or age - can inadvertently affect another, like gender, either mitigating or exacerbating existing disparities. Understanding these interdependencies is crucial for designing fairer generative models, yet measuring such effects quantitatively remains a challenge. To address this, we introduce BiasConnect, a novel tool for analyzing and quantifying bias interactions in TTI models. BiasConnect uses counterfactual interventions along different bias axes to reveal the underlying structure of these interactions and estimates the effect of mitigating one bias axis on another. These estimates show strong correlation (+0.65) with observed post-mitigation outcomes. Building on BiasConnect, we propose InterMit, an intersectional bias mitigation algorithm guided by user-defined target distributions and priority weights. InterMit achieves lower bias (0.33 vs. 0.52) with fewer mitigation steps (2.38 vs. 3.15 average steps), and yields superior image quality compared to traditional techniques. Although our implementation is training-free, InterMit is modular and can be integrated with many existing debiasing approaches for TTI models, making it a flexible and extensible solution.