FairCoT: Enhancing Fairness in Diffusion Models via Chain of Thought Reasoning of Multimodal Language Models
Keywords: diffusion models;fairness; bias; chain of thought; text to image; multimodal LLMs
Abstract: In the domain of text-to-image generative models, biases inherent in training datasets often propagate into generated content, posing significant ethical challenges, particularly in socially sensitive contexts. We introduce FairCoT, a novel framework that enhances fairness in diffusion models through Chain-of-Thought (CoT) reasoning within multimodal generative large language models (LLMs). FairCoT employs iterative CoT refinement and attire-based attribute prediction to systematically mitigate biases, ensuring diverse and equitable representation in generated images. By integrating iterative reasoning processes, FairCoT addresses the limitations of zero-shot CoT in sensitive scenarios, balancing creativity with ethical responsibility. Experimental evaluations across multiple models, including DALL-E and various Stable Diffusion variants, demonstrate that FairCoT significantly improves fairness and diversity metrics without compromising image quality or relevance. Our approach advances ethical AI practices in generative modeling, promoting socially responsible content generation and setting new standards for fairness in AI-generated imagery.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8217
Loading