FairCoT：通过多模态大语言模型的思维链推理增强文本到图像生成中的公平性
FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Models
AI总结：
本文提出FairCoT框架，通过多模态大语言模型中的迭代思维链推理动态调整文本提示，有效减轻文本到图像生成中的偏见，在DALLE和Stable Diffusion等模型上显著提升了公平性与多样性，且不牺牲图像质量。
摘要：
在文本到图像生成模型领域，训练数据集中固有的偏见通常会传播到生成内容中，带来了重大的伦理挑战，尤其是在社会敏感场景中。我们引入了FairCoT，这是一种新颖的框架，通过多模态生成大语言模型内的思维链（CoT）推理来增强文本到图像模型的公平性。FairCoT采用迭代CoT细化来系统地减轻偏见，并实时动态调整文本提示，确保生成图像中具有多样且公平的表征。通过整合迭代推理过程，FairCoT解决了零样本CoT在敏感场景中的局限性，平衡了创造力与伦理责任。在包括DALLE和各种Stable Diffusion变体在内的流行文本到图像系统上进行的实验评估表明，FairCoT显著增强了公平性和多样性，同时没有牺牲图像质量或语义保真度。通过结合稳健的推理、轻量级部署以及对多模型的可扩展性，FairCoT代表着朝着更具社会责任感和透明度的AI驱动内容生成迈出的有希望的一步。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
