Exploring Bias in over 100 Text-to-Image Generative Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909533723426816 |
|---|---|
| author | Vice, Jordan Akhtar, Naveed Hartley, Richard Mian, Ajmal |
| author_facet | Vice, Jordan Akhtar, Naveed Hartley, Richard Mian, Ajmal |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08012 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Bias in over 100 Text-to-Image Generative Models Vice, Jordan Akhtar, Naveed Hartley, Richard Mian, Ajmal Computer Vision and Pattern Recognition Artificial Intelligence 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 |
| title | Exploring Bias in over 100 Text-to-Image Generative Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.08012 |