T-HITL 有效解决图像生成中的问题性关联并保持整体视觉质量
T-HITL Effectively Addresses Problematic Associations in Image Generation and Maintains Overall Visual Quality
AI总结:
本文提出双重人在回路方法 T-HITL,在模型层面减少图像生成中的人口统计群体与语义概念之间的有害关联,同时保持生成图像的视觉质量,避免传统微调导致的质量下降。
摘要:
生成式 AI 图像模型可能会无意中生成有问题的人物表征。过去的研究指出,全球每天有数百万用户使用这些模型,而这些模型——包括通过有问题的人物表征——有可能加剧并加速现实世界中的歧视和其他危害(Bianchi 等人,2023)。在本文中,我们专注于解决人口统计群体与语义概念之间问题性关联的生成问题,这些关联可能反映并强化嵌入在社会数据中的负面叙事。基于社会学文献(Blumer,1958)并将表征映射到模型行为,我们开发了一个分类体系来研究图像生成模型中的问题性关联。我们探索了在模型层面进行微调作为解决这些关联的方法的有效性,并识别出传统微调的一个局限性是可能导致视觉质量下降。我们还提出了一种新的方法,即双重人在回路(T-HITL),该方法有望在减少问题性关联和保持视觉质量两方面都带来改进。我们通过提供 T-HITL 在模型层面解决的三个问题性关联的证据来证明 T-HITL 的有效性。我们对学术研究的贡献是双重的。通过在机器学习模型和生成式 AI 的语境中定义问题性关联,我们引入了一个概念性和技术性的分类体系来处理其中一些关联。最后,我们提供了一种方法 T-HITL,它既能解决这些关联,又能同时保持图像模型生成结果的视觉质量。这种缓解不必是一种权衡,而是一种增强。
英文摘要:
Generative AI image models may inadvertently generate problematic representations of people. Past research has noted that millions of users engage daily across the world with these models and that the models, including through problematic representations of people, have the potential to compound and accelerate real-world discrimination and other harms (Bianchi et al, 2023). In this paper, we focus on addressing the generation of problematic associations between demographic groups and semantic concepts that may reflect and reinforce negative narratives embedded in social data. Building on sociological literature (Blumer, 1958) and mapping representations to model behaviors, we have developed a taxonomy to study problematic associations in image generation models. We explore the effectiveness of fine tuning at the model level as a method to address these associations, identifying a potential reduction in visual quality as a limitation of traditional fine tuning. We also propose a new methodology with twice-human-in-the-loop (T-HITL) that promises improvements in both reducing problematic associations and also maintaining visual quality. We demonstrate the effectiveness of T-HITL by providing evidence of three problematic associations addressed by T-HITL at the model level. Our contributions to scholarship are two-fold. By defining problematic associations in the context of machine learning models and generative AI, we introduce a conceptual and technical taxonomy for addressing some of these associations. Finally, we provide a method, T-HITL, that addresses these associations and simultaneously maintains visual quality of image model generations. This mitigation need not be a tradeoff, but rather an enhancement.
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。