FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Models

TL;DR

FairCoT is a framework that improves fairness and diversity in text-to-image generation by using iterative chain of thought reasoning within multimodal large language models, addressing biases and ethical concerns.

Contribution

It introduces FairCoT, a novel method that leverages iterative reasoning and prompt adjustment to mitigate biases in text-to-image models, enhancing fairness without reducing image quality.

Findings

Significantly improves fairness and diversity in generated images.

Maintains image quality and semantic fidelity.

Effective across multiple popular models like DALLE and Stable Diffusion.

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 text to image models through Chain of Thought (CoT) reasoning within multimodal generative large language models. FairCoT employs iterative CoT refinement to systematically mitigate biases, and dynamically adjusts textual prompts in real time, 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 popular text-to-image systems including DALLE and various Stable Diffusion variants, demonstrate that FairCoT significantly enhances fairness and diversity without sacrificing image quality or semantic fidelity. By combining robust reasoning, lightweight deployment, and extensibility to multiple models, FairCoT represents a promising step toward more socially responsible and transparent AI driven content generation.