# Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models

arXiv: https://arxiv.org/abs/2312.10065 · HTML: https://mlsanity.com/paper/2312.10065/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 5 Dec 2023.

## Placed in

- 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, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset](https://mlsanity.com/paper/2104.09957/) (2021)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions](https://mlsanity.com/paper/2305.18047/) (2023)
- [Diffusion Models for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2306.09316/) (2023)
- [Analyzing Bias in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2305.06402/) (2023)
- [Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation](https://mlsanity.com/paper/2004.08945/) (2020)
- [American == White in Multimodal Language-and-Image AI](https://mlsanity.com/paper/2207.00691/) (2022)
- [T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation](https://mlsanity.com/paper/2306.00905/) (2023)
- [Towards Transparency in Dermatology Image Datasets with Skin Tone Annotations by Experts, Crowds, and an Algorithm](https://mlsanity.com/paper/2207.02942/) (2022)
- [Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets](https://mlsanity.com/paper/1910.13268/) (2019)
- [Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation](https://mlsanity.com/paper/2308.05441/) (2023)
- [Intersectional Bias in Causal Language Models](https://mlsanity.com/paper/2107.07691/) (2021)
- [Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models](https://mlsanity.com/paper/2112.07447/) (2021)
- [Evaluating Biased Attitude Associations of Language Models in an Intersectional Context](https://mlsanity.com/paper/2307.03360/) (2023)
- [Human Skin Detection Using RGB, HSV and YCbCr Color Models](https://mlsanity.com/paper/1708.02694/) (2017)
- [WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings](https://mlsanity.com/paper/2103.03598/) (2021)

## Built on by (most cited first, 7 of 7)

- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [Harm Amplification in Text-to-Image Models](https://mlsanity.com/paper/2402.01787/) (2024)
- [In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models](https://mlsanity.com/paper/2409.15454/) (2024)
- [KAHANI: Culturally-Nuanced Visual Storytelling Tool for Non-Western Cultures](https://mlsanity.com/paper/2410.19419/) (2024)
- [An Exploration of Default Images in Text-to-Image Generation](https://mlsanity.com/paper/2505.09166/) (2025)
- [Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundational Models](https://mlsanity.com/paper/2408.01431/) (2024)

## Abstract (arXiv)

Text-to-image diffusion models have been adopted into key commercial workflows, such as art generation and image editing. Characterising the implicit social biases they exhibit, such as gender and racial stereotypes, is a necessary first step in avoiding discriminatory outcomes. While existing studies on social bias focus on image generation, the biases exhibited in alternate applications of diffusion-based foundation models remain under-explored. We propose methods that use synthetic images to probe two applications of diffusion models, image editing and classification, for social bias. Using our methodology, we uncover meaningful and significant inter-sectional social biases in textitStable Diffusion, a state-of-the-art open-source text-to-image model. Our findings caution against the uninformed adoption of text-to-image foundation models for downstream tasks and services.