mlsanityData to 14 Oct 2026

OpenBias: Open-set Bias Detection in Text-to-Image Generative Models

arXiv 2404.07990 ↗First posted 11 Apr 2024cs.CV cs.AIcited by 61

Not on the map. Why?

Abstract (arXiv)

Text-to-image generative models are becoming increasingly popular and accessible to the general public. As these models see large-scale deployments, it is necessary to deeply investigate their safety and fairness to not disseminate and perpetuate any kind of biases. However, existing works focus on detecting closed sets of biases defined a priori, limiting the studies to well-known concepts. In this paper, we tackle the challenge of open-set bias detection in text-to-image generative models presenting OpenBias, a new pipeline that identifies and quantifies the severity of biases agnostically, without access to any precompiled set. OpenBias has three stages. In the first phase, we leverage a Large Language Model (LLM) to propose biases given a set of captions. Secondly, the target generative model produces images using the same set of captions. Lastly, a Vision Question Answering model recognizes the presence and extent of the previously proposed biases. We study the behavior of Stable Diffusion 1.5, 2, and XL emphasizing new biases, never investigated before. Via quantitative experiments, we demonstrate that OpenBias agrees with current closed-set bias detection methods and human judgement.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Builds on 63 of its 77 references that are in the map. First posted on arXiv 11 Apr 2024.

Builds on

63 of 77 references.

References · 63

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  9. 2023Visual Instruction Tuningcited by 7,869
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  11. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  12. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
38 more
  1. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2022Classifier-Free Diffusion Guidancecited by 5,847
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  7. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  10. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  11. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  12. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  13. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  14. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  15. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  16. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  17. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
  18. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  19. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 745
  20. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 659
  21. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  22. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
  23. 2022GIT: A Generative Image-to-text Transformer for Vision and Languagecited by 537
  24. 2022Visual Programming: Compositional visual reasoning without trainingcited by 516
  25. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 428
  26. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  27. 2023Unified Concept Editing in Diffusion Modelscited by 388
  28. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  29. 2023Composer: Creative and Controllable Image Synthesis with Composable Conditionscited by 304
  30. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  31. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  32. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 243
  33. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  34. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  35. 2022SpaText: Spatio-Textual Representation for Controllable Image Generationcited by 217
  36. 2022mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connectionscited by 187
  37. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  38. 2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 151

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 14; 2025: 34; 2026: 13.

61 papers.

Sort:

By area:

  1. 2025HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluationcited by 19
  2. 2025A Large Scale Analysis of Gender Biases in Text-to-Image Generative Modelscited by 14
  3. 2024Backdooring Bias (B2) into Stable Diffusion Modelscited by 12
  4. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  5. 2025Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generationcited by 11
  6. 2025Culture in Action: Evaluating Text-to-Image Models through Social Activitiescited by 10
  7. 2024Analyzing Quality, Bias, and Performance in Text-to-Image Generative Modelscited by 9
  8. 2025Re-Imagining Multimodal Instruction Tuning: A Representation Viewcited by 9
  9. 2025Exploring Bias in over 100 Text-to-Image Generative Modelscited by 9
  10. 2025OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypescited by 8
  11. 2024Organizing Unstructured Image Collections using Natural Languagecited by 7
  12. 2024Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Surveycited by 6
38 more
  1. 2025POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generationcited by 6
  2. 2024GRADE: Quantifying Sample Diversity in Text-to-Image Modelscited by 5
  3. 2024MAVias: Mitigate any Visual Biascited by 5
  4. 2024Say My Name: a Model's Bias Discovery Frameworkcited by 4
  5. 2025Implicit Bias Injection Attacks against Text-to-Image Diffusion Modelscited by 4
  6. 2025Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifierscited by 4
  7. 2025DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Modelscited by 4
  8. 2025How I Met Your Bias: Investigating Bias Amplification in Diffusion Modelscited by 4
  9. 2025Diffusing DeBias: Synthetic Bias Amplification for Model Debiasingcited by 3
  10. 2025Group-robust Machine Unlearningcited by 3
  11. 2025Multi-Group Proportional Representation for Text-to-Image Modelscited by 3
  12. 2025Processing and acquisition traces in visual encoders: What does CLIP know about your camera?cited by 3
  13. 2025RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generationcited by 3
  14. 2024GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Modelscited by 2
  15. 2024Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Modelscited by 2
  16. 2024On the Fairness, Diversity and Reliability of Text-to-Image Generative Modelscited by 2
  17. 2024GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifierscited by 2
  18. 2025BiasConnect: Investigating Bias Interactions in Text-to-Image Modelscited by 2
  19. 2025Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQAcited by 2
  20. 2025Discovering Divergent Representations between Text-to-Image Modelscited by 2
  21. 2025BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generationcited by 2
  22. 2025Automated Detection of Visual Attribute Reliance with a Self-Reflective Agentcited by 2
  23. 2026VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigationcited by 2
  24. 2026Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generationcited by 2
  25. 2024AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generationcited by 1
  26. 2024Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstructioncited by 1
  27. 2025Safe Vision-Language Models via Unsafe Weights Manipulationcited by 1
  28. 2025Synthetic History: Evaluating Visual Representations of the Past in Diffusion Modelscited by 1
  29. 2025How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Modelscited by 1
  30. 2025MineTheGap: Automatic Mining of Biases in Text-to-Image Modelscited by 1
  31. 2026SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Modelscited by 1
  32. 2026Bias at the End of the Scorecited by 1
  33. 2026Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Modelscited by 1
  34. 2026StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMscited by 1
  35. 2025FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancingcited by 0
  36. 2025ImageSet2Text: Describing Sets of Images through Textcited by 0
  37. 2025Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activitiescited by 0
  38. 2025Improving Fairness in LLMs Through Testing-Time Adversariescited by 0

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
  2. 2024BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models
  3. 2024Uncovering Bias in Large Vision-Language Models with Counterfactuals
  4. 2024Manipulating and Mitigating Generative Model Biases without Retraining
  5. 2024Debiasing Multimodal Large Language Models via Penalization of Language Priors
  6. 2023Debiasing Vision-Language Models via Biased Prompts
  7. 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
  8. 2023MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Models