# Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples

arXiv: https://arxiv.org/abs/2310.02988 · HTML: https://mlsanity.com/paper/2310.02988/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 19 references that are in the map.
- First posted on arXiv 4 Oct 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Social bias and fairness in VLMs](https://mlsanity.com/mllm/social-bias-and-fairness-in-vlms/)
- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search](https://mlsanity.com/paper/1905.01989/) (2019)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [ALIP: Adaptive Language-Image Pre-training with Synthetic Caption](https://mlsanity.com/paper/2308.08428/) (2023)
- [Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks](https://mlsanity.com/paper/2306.05550/) (2023)
- [COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs](https://mlsanity.com/paper/2309.14356/) (2023)
- [Run Like a Girl! Sports-Related Gender Bias in Language and Vision](https://mlsanity.com/paper/2305.14468/) (2023)

## Built on by (most cited first, 5 of 5)

- [Benchmarking Segmentation Models with Mask-Preserved Attribute Editing](https://mlsanity.com/paper/2403.01231/) (2024)
- [Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles](https://mlsanity.com/paper/2311.16176/) (2023)
- [VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models](https://mlsanity.com/paper/2505.22897/) (2025)
- [Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing](https://mlsanity.com/paper/2603.01535/) (2026)
- [RS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion Models](https://mlsanity.com/paper/2312.04810/) (2023)

## Abstract (arXiv)

While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect to social attributes such as gender and race. Prior studies have primarily focused on probing such bias attributes individually while ignoring biases associated with intersections between social attributes. This could be due to the difficulty of collecting an exhaustive set of image-text pairs for various combinations of social attributes from existing datasets. To address this challenge, we employ text-to-image diffusion models to produce counterfactual examples for probing intserctional social biases at scale. Our approach utilizes Stable Diffusion with cross attention control to produce sets of counterfactual image-text pairs that are highly similar in their depiction of a subject (e.g., a given occupation) while differing only in their depiction of intersectional social attributes (e.g., race & gender). We conduct extensive experiments using our generated dataset which reveal the intersectional social biases present in state-of-the-art VLMs.