mlsanityData to 7 Oct 2026

A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models

arXiv 2503.23398 ↗First posted 30 Mar 2025cs.CV cs.CYcited by 12

Not on the map. Why?

Abstract (arXiv)

With the increasing use of image generation technology, understanding its social biases, including gender bias, is essential. This paper presents a large-scale study on gender bias in text-to-image (T2I) models, focusing on everyday situations. While previous research has examined biases in occupations, we extend this analysis to gender associations in daily activities, objects, and contexts. We create a dataset of 3,217 gender-neutral prompts and generate 200 images over 5 prompt variations per prompt from five leading T2I models. We automatically detect the perceived gender of people in the generated images and filter out images with no person or multiple people of different genders, leaving 2,293,295 images. To enable a broad analysis of gender bias in T2I models, we group prompts into semantically similar concepts and calculate the proportion of male- and female-gendered images for each prompt. Our analysis shows that T2I models reinforce traditional gender roles and reflect common gender stereotypes in household roles. Women are predominantly portrayed in care and human-centered scenarios, and men in technical or physical labor scenarios.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 78 of its 125 references that are in the map. First posted on arXiv 30 Mar 2025.

Builds on

78 of 125 references.

References · 78

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2024Qwen2.5 Technical Reportcited by 4,713
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  8. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  9. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  10. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  11. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  12. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
38 more
  1. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  2. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  3. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  4. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  5. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  6. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 787
  7. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
  8. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  9. 2023Adversarial Diffusion Distillationcited by 741
  10. 2024Yi: Open Foundation Models by 01.AIcited by 706
  11. 2024Phi-4 Technical Reportcited by 675
  12. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615
  13. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  14. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 465
  15. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
  16. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  17. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  18. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  19. 2023Stable Bias: Analyzing Societal Representations in Diffusion Modelscited by 225
  20. 2023StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learnerscited by 177
  21. 2024Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretrainingcited by 148
  22. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 134
  23. 2021Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implicationscited by 128
  24. 2023Scaling Laws of Synthetic Images for Model Training ... for Nowcited by 107
  25. 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
  26. 2017Accelerated Hierarchical Density Clusteringcited by 100
  27. 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?cited by 92
  28. 2024No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performancecited by 75
  29. 2023Learning Vision from Models Rivals Learning Vision from Datacited by 71
  30. 2023DeAR: Debiasing Vision-Language Models with Additive Residualscited by 70
  31. 2023Questioning the Survey Responses of Large Language Modelscited by 70
  32. 2023The Bias Amplification Paradox in Text-to-Image Generationcited by 69
  33. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  34. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
  35. 2024OpenBias: Open-set Bias Detection in Text-to-Image Generative Modelscited by 61
  36. 2024Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Imagescited by 55
  37. 2023SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examplescited by 53
  38. 2023VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolutioncited by 52

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 6.

12 papers.

  1. 2025Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Modelscited by 4
  2. 2025Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencodercited by 3
  3. 2025Early Estimation of Language to Latent Alignment in Diffusion Modelscited by 3
  4. 2025From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationshipcited by 2
  5. 2025Invisible Attributes, Visible Biases: Exploring Demographic Shortcuts in MRI-based Alzheimer's Disease Classificationcited by 2
  6. 2026Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scalescited by 2
  7. 2026Investigating Associational Biases in Inter-Model Communication of Large Generative Modelscited by 1
  8. 2026Bias at the End of the Scorecited by 1
  9. 2025Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Searchcited by 0
  10. 2026Identifying Ethical Biases in Action Recognition Modelscited by 0
  11. 2026Beyond wheelchairs and blindfolds: Investigating disability stereotypes in T2I models with INCLUDE-BENCHcited by 0
  12. 2026ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Modelscited by 0