mlsanityData to 14 Oct 2026

Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale

arXiv 2211.03759 ↗First posted 7 Nov 2022cs.CL cs.CVcited by 262

Not on the map. Why?

Cited by 52 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day. We investigate the potential for these models to amplify dangerous and complex stereotypes. We find a broad range of ordinary prompts produce stereotypes, including prompts simply mentioning traits, descriptors, occupations, or objects. For example, we find cases of prompting for basic traits or social roles resulting in images reinforcing whiteness as ideal, prompting for occupations resulting in amplification of racial and gender disparities, and prompting for objects resulting in reification of American norms. Stereotypes are present regardless of whether prompts explicitly mention identity and demographic language or avoid such language. Moreover, stereotypes persist despite mitigation strategies; neither user attempts to counter stereotypes by requesting images with specific counter-stereotypes nor institutional attempts to add system ``guardrails'' have prevented the perpetuation of stereotypes. Our analysis justifies concerns regarding the impacts of today's models, presenting striking exemplars, and connecting these findings with deep insights into harms drawn from social scientific and humanist disciplines. This work contributes to the effort to shed light on the uniquely complex biases in language-vision models and demonstrates the ways that the mass deployment of text-to-image generation models results in mass dissemination of stereotypes and resulting harms.

Key facts. Cited by 262 papers in the map (data through 14 Oct 2026). Builds on 21 of its 87 references that are in the map. First posted on arXiv 7 Nov 2022.

Builds on

21 of 87 references.

References · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2021Ethical and social risks of harm from Language Modelscited by 966
  5. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  6. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
  7. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 327
  8. 2020Data and its (dis)contents: A survey of dataset development and use in machine learning researchcited by 260
  9. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 253
  10. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  11. 2019Does Object Recognition Work for Everyone?cited by 151
  12. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
9 more
  1. 2017Deceiving Google's Perspective API Built for Detecting Toxic Commentscited by 102
  2. 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?cited by 92
  3. 2021Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Searchcited by 90
  4. 2020Measuring Social Biases in Grounded Vision and Language Embeddingscited by 61
  5. 2022American == White in Multimodal Language-and-Image AIcited by 39
  6. 2022Evidence for Hypodescent in Visual Semantic AIcited by 30
  7. 2022Markedness in Visual Semantic AIcited by 29
  8. 2019Female Librarians and Male Computer Programmers? Gender Bias in Occupational Images on Digital Media Platformscited by 13
  9. 2021Social Norm Bias: Residual Harms of Fairness-Aware Algorithmscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 50; 2024: 83; 2025: 76; 2026: 48.

262 papers.

Sort:

By area:

  1. 2023Unified Concept Editing in Diffusion Modelscited by 388
  2. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 268
  3. 2023SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionalitycited by 243
  4. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 189
  5. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 172
  6. 2023Holistic Evaluation of Text-To-Image Modelscited by 160
  7. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 157
  8. 2023LEDITS++: Limitless Image Editing using Text-to-Image Modelscited by 148
  9. 2023Editing Implicit Assumptions in Text-to-Image Diffusion Modelscited by 130
  10. 2023Social Biases through the Text-to-Image Generation Lenscited by 127
  11. 2023Finetuning Text-to-Image Diffusion Models for Fairnesscited by 92
  12. 2024Large-scale Reinforcement Learning for Diffusion Modelscited by 78
38 more
  1. 2024SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safetycited by 77
  2. 2023Data Quality in Imitation Learningcited by 75
  3. 2023The Bias Amplification Paradox in Text-to-Image Generationcited by 70
  4. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  5. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
  6. 2024OpenBias: Open-set Bias Detection in Text-to-Image Generative Modelscited by 61
  7. 2022Will Large-scale Generative Models Corrupt Future Datasets?cited by 59
  8. 2024Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Imagescited by 55
  9. 2023AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asiacited by 54
  10. 2023Uncurated Image-Text Datasets: Shedding Light on Demographic Biascited by 52
  11. 2023TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Modelscited by 52
  12. 2024LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Modelscited by 52
  13. 2025T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generationcited by 48
  14. 2024Margin-aware Preference Optimization for Aligning Diffusion Models without Referencecited by 46
  15. 2023Inspecting the Geographical Representativeness of Images from Text-to-Image Modelscited by 44
  16. 2022Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Biascited by 43
  17. 2023Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Modelscited by 41
  18. 2023T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generationcited by 39
  19. 2023COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairscited by 39
  20. 2023Interpretable Diffusion via Information Decompositioncited by 37
  21. 2023ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languagescited by 34
  22. 2024FairRAG: Fair Human Generation via Fair Retrieval Augmentationcited by 34
  23. 2023Feedback-guided Data Synthesis for Imbalanced Classificationcited by 33
  24. 2023ReFACT: Updating Text-to-Image Models by Editing the Text Encodercited by 32
  25. 2023Labeling Neural Representations with Inverse Recognitioncited by 32
  26. 2024GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probingcited by 31
  27. 2024Beyond Aesthetics: Cultural Competence in Text-to-Image Modelscited by 30
  28. 2023Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Modelscited by 27
  29. 2024ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generationcited by 27
  30. 2024Identifying Implicit Social Biases in Vision-Language Modelscited by 27
  31. 2024Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approachcited by 26
  32. 2023Stable Diffusion Exposed: Gender Bias from Prompt to Imagecited by 25
  33. 2024Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertaintycited by 25
  34. 2024From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agentscited by 25
  35. 2024Would Deep Generative Models Amplify Bias in Future Models?cited by 24
  36. 2024Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidancecited by 24
  37. 2022The Stable Artist: Steering Semantics in Diffusion Latent Spacecited by 23
  38. 2023Auditing Gender Presentation Differences in Text-to-Image Modelscited by 22

50 most cited of 262 All 262 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Hidden Bias in the Machine: Stereotypes in Text-to-Image Models
  2. 2025Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations
  3. 2023RS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion Models
  4. 2025Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models
  5. 2023Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models
  6. 2024Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models
  7. 2025Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity
  8. 2025SCALEX: Scalable Concept and Latent Exploration for Diffusion Models