# T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Models

arXiv: https://arxiv.org/abs/2511.10089 · HTML: https://mlsanity.com/paper/2511.10089/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 13 Nov 2025.

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](https://mlsanity.com/paper/2402.13929/) (2024)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics](https://mlsanity.com/paper/2106.14574/) (2021)
- [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024)
- [Large-scale Text-to-Image Generation Models for Visual Artists' Creative Works](https://mlsanity.com/paper/2210.08477/) (2022)
- [FACET: Fairness in Computer Vision Evaluation Benchmark](https://mlsanity.com/paper/2309.00035/) (2023)
- [RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model](https://mlsanity.com/paper/2309.00810/) (2023)
- [Norm-guided latent space exploration for text-to-image generation](https://mlsanity.com/paper/2306.08687/) (2023)
- [HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving](https://mlsanity.com/paper/2401.03160/) (2024)
- [Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework](https://mlsanity.com/paper/2410.21061/) (2024)
- [Quantifying Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.13053/) (2023)
- [New Job, New Gender? Measuring the Social Bias in Image Generation Models](https://mlsanity.com/paper/2401.00763/) (2024)
- [Discovering Bias in Latent Space: An Unsupervised Debiasing Approach](https://mlsanity.com/paper/2406.03631/) (2024)
- [CTR-Driven Advertising Image Generation with Multimodal Large Language Models](https://mlsanity.com/paper/2502.06823/) (2025)
- [Exploring Bias in over 100 Text-to-Image Generative Models](https://mlsanity.com/paper/2503.08012/) (2025)
- [Latent Directions: A Simple Pathway to Bias Mitigation in Generative AI](https://mlsanity.com/paper/2406.06352/) (2024)
- [Learning Diffusion Model from Noisy Measurement using Principled Expectation-Maximization Method](https://mlsanity.com/paper/2410.11241/) (2024)

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

- [Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generation](https://mlsanity.com/paper/2602.00032/) (2026)
- [Toward Trustworthy Portrait Editing: Evaluation of Demographic Misrepresentation in I2I Models](https://mlsanity.com/paper/2602.16149/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) generative models are largely used in AI-powered real-world applications and value creation. However, their strategic deployment raises critical concerns for responsible AI management, particularly regarding the reproduction and amplification of race- and gender-related stereotypes that can undermine organizational ethics. In this work, we investigate whether such societal biases are systematically encoded within the pretrained latent spaces of state-of-the-art T2I models. We conduct an empirical study across the five most popular open-source models, using ten neutral, profession-related prompts to generate 100 images per profession, resulting in a dataset of 5,000 images evaluated by diverse human assessors representing different races and genders. We demonstrate that all five models encode and amplify pronounced societal skew: caregiving and nursing roles are consistently feminized, while high-status professions such as corporate CEO, politician, doctor, and lawyer are overwhelmingly represented by males and mostly White individuals. We further identify model-specific patterns, such as QWEN-Image's near-exclusive focus on East Asian outputs, Kandinsky's dominance of White individuals, and SDXL's comparatively broader but still biased distributions. These results provide critical insights for AI project managers and practitioners, enabling them to select equitable AI models and customized prompts that generate images in alignment with the principles of responsible AI. We conclude by discussing the risks of these biases and proposing actionable strategies for bias mitigation in building responsible GenAI systems. The code and Data Repository: https://github.com/Sufianlab/T2IBias