# Social Biases through the Text-to-Image Generation Lens

arXiv: https://arxiv.org/abs/2304.06034 · HTML: https://mlsanity.com/paper/2304.06034/

## Key facts

- Cited by 127 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [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)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](https://mlsanity.com/paper/2204.14217/) (2022)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age](https://mlsanity.com/paper/1908.04913/) (2019)
- [Auditing Gender Presentation Differences in Text-to-Image Models](https://mlsanity.com/paper/2302.03675/) (2023)
- [Max-Margin Object Detection](https://mlsanity.com/paper/1502.00046/) (2015)

## Built on by (most cited first, 30 of 127)

- [UltraEdit: Instruction-based Fine-Grained Image Editing at Scale](https://mlsanity.com/paper/2407.05282/) (2024)
- [AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea](https://mlsanity.com/paper/2411.15738/) (2024)
- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [Large-scale Reinforcement Learning for Diffusion Models](https://mlsanity.com/paper/2401.12244/) (2024)
- [The Bias Amplification Paradox in Text-to-Image Generation](https://mlsanity.com/paper/2308.00755/) (2023)
- [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024)
- [OpenBias: Open-set Bias Detection in Text-to-Image Generative Models](https://mlsanity.com/paper/2404.07990/) (2024)
- [SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2312.00825/) (2023)
- [Analyzing Bias in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2305.06402/) (2023)
- [Inspecting the Geographical Representativeness of Images from Text-to-Image Models](https://mlsanity.com/paper/2305.11080/) (2023)
- [DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization](https://mlsanity.com/paper/2410.16942/) (2024)
- [If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection](https://mlsanity.com/paper/2305.13308/) (2023)
- [An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance](https://mlsanity.com/paper/2404.01247/) (2024)
- [Beyond Aesthetics: Cultural Competence in Text-to-Image Models](https://mlsanity.com/paper/2407.06863/) (2024)
- [ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation](https://mlsanity.com/paper/2401.06310/) (2024)
- [Stable Diffusion Exposed: Gender Bias from Prompt to Image](https://mlsanity.com/paper/2312.03027/) (2023)
- [Prompt Expansion for Adaptive Text-to-Image Generation](https://mlsanity.com/paper/2312.16720/) (2023)
- [Would Deep Generative Models Amplify Bias in Future Models?](https://mlsanity.com/paper/2404.03242/) (2024)
- [Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance](https://mlsanity.com/paper/2406.04551/) (2024)
- [Distribution-Aware Data Expansion with Diffusion Models](https://mlsanity.com/paper/2403.06741/) (2024)
- [Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation](https://mlsanity.com/paper/2403.12075/) (2024)
- [Constrained Diffusion Models via Dual Training](https://mlsanity.com/paper/2408.15094/) (2024)
- [Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models](https://mlsanity.com/paper/2310.01929/) (2023)
- [Quantifying Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.13053/) (2023)
- [Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You](https://mlsanity.com/paper/2401.16092/) (2024)
- [Harm Amplification in Text-to-Image Models](https://mlsanity.com/paper/2402.01787/) (2024)
- [Deepfakes on Demand: the rise of accessible non-consensual deepfake image generators](https://mlsanity.com/paper/2505.03859/) (2025)
- [CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics](https://mlsanity.com/paper/2506.08835/) (2025)
- [From Melting Pots to Misrepresentations: Exploring Harms in Generative AI](https://mlsanity.com/paper/2403.10776/) (2024)
- [A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models](https://mlsanity.com/paper/2307.12980/) (2023)

## Abstract (arXiv)

Text-to-Image (T2I) generation is enabling new applications that support creators, designers, and general end users of productivity software by generating illustrative content with high photorealism starting from a given descriptive text as a prompt. Such models are however trained on massive amounts of web data, which surfaces the peril of potential harmful biases that may leak in the generation process itself. In this paper, we take a multi-dimensional approach to studying and quantifying common social biases as reflected in the generated images, by focusing on how occupations, personality traits, and everyday situations are depicted across representations of (perceived) gender, age, race, and geographical location. Through an extensive set of both automated and human evaluation experiments we present findings for two popular T2I models: DALLE-v2 and Stable Diffusion. Our results reveal that there exist severe occupational biases of neutral prompts majorly excluding groups of people from results for both models. Such biases can get mitigated by increasing the amount of specification in the prompt itself, although the prompting mitigation will not address discrepancies in image quality or other usages of the model or its representations in other scenarios. Further, we observe personality traits being associated with only a limited set of people at the intersection of race, gender, and age. Finally, an analysis of geographical location representations on everyday situations (e.g., park, food, weddings) shows that for most situations, images generated through default location-neutral prompts are closer and more similar to images generated for locations of United States and Germany.