mlsanityData to 14 Oct 2026

Exploring Bias in over 100 Text-to-Image Generative Models

arXiv 2503.08012 ↗First posted 11 Mar 2025cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

We investigate bias trends in text-to-image generative models over time, focusing on the increasing availability of models through open platforms like Hugging Face. While these platforms democratize AI, they also facilitate the spread of inherently biased models, often shaped by task-specific fine-tuning. Ensuring ethical and transparent AI deployment requires robust evaluation frameworks and quantifiable bias metrics. To this end, we assess bias across three key dimensions: (i) distribution bias, (ii) generative hallucination, and (iii) generative miss-rate. Analyzing over 100 models, we reveal how bias patterns evolve over time and across generative tasks. Our findings indicate that artistic and style-transferred models exhibit significant bias, whereas foundation models, benefiting from broader training distributions, are becoming progressively less biased. By identifying these systemic trends, we contribute a large-scale evaluation corpus to inform bias research and mitigation strategies, fostering more responsible AI development. Keywords: Bias, Ethical AI, Text-to-Image, Generative Models, Open-Source Models

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 42 of its 46 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

42 of 46 references.

References · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  11. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
30 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  3. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  4. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  6. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  7. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  8. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 513
  9. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  10. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 428
  11. 2023Unified Concept Editing in Diffusion Modelscited by 388
  12. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 377
  13. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  14. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 329
  15. 2023Detecting and Preventing Hallucinations in Large Vision Language Modelscited by 256
  16. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  17. 2023Stable Bias: Analyzing Societal Representations in Diffusion Modelscited by 226
  18. 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 148
  19. 2023Social Biases through the Text-to-Image Generation Lenscited by 127
  20. 2023HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Modelscited by 95
  21. 2023The Bias Amplification Paradox in Text-to-Image Generationcited by 70
  22. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
  23. 2024OpenBias: Open-set Bias Detection in Text-to-Image Generative Modelscited by 61
  24. 2023Uncurated Image-Text Datasets: Shedding Light on Demographic Biascited by 52
  25. 2023TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Modelscited by 52
  26. 2023Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Modelscited by 42
  27. 2021Measuring Fairness in Generative Modelscited by 31
  28. 2022VALHALLA: Visual Hallucination for Machine Translationcited by 27
  29. 2024FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Modelscited by 22
  30. 2023Quantifying Bias in Text-to-Image Generative Modelscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 2.

9 papers.

  1. 2025Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoningcited by 33
  2. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 27
  3. 2025FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RLcited by 13
  4. 2025ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentationcited by 3
  5. 2025T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Modelscited by 2
  6. 2026The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Modelscited by 2
  7. 2025Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activitiescited by 0
  8. 2025When Cars Have Stereotypes: Auditing Demographic Bias in Objects from Text-to-Image Modelscited by 0
  9. 2026KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generationcited by 0