解构偏见：用于诊断文本到图像生成模型中文化与构成不平等的多层面框架
Deconstructing Bias: A Multifaceted Framework for Diagnosing Cultural and Compositional Inequities in Text-to-Image Generative Models
AI总结：
本文提出组件包含分数（CIS）指标，通过分析2,400张图像量化文本到图像模型在西方与非西方文化提示间的偏见，揭示数据不平衡、注意力熵和嵌入叠加对公平性的影响，并为提升文化包容性提供架构与数据层面的干预见解。
摘要：
文本到图像（T2I）模型的变革潜力取决于其根据文本提示合成文化多样、照片级真实图像的能力。然而，这些模型往往会延续其训练数据中嵌入的文化偏见，导致系统性错误表征。本文对组件包含分数（Component Inclusion Score，CIS）进行了基准评估，该指标旨在评估图像生成在不同文化语境下的保真度。通过对2,400张图像的广泛分析，我们从构成脆弱性和语境错位两方面量化了偏见，揭示了西方与非西方文化提示之间存在显著的性能差距。我们的研究结果强调了数据不平衡、注意力熵和嵌入叠加对模型公平性的影响。通过使用CIS对Stable Diffusion等模型进行基准测试，我们为增强AI生成图像中文化包容性的架构层面和数据层面干预措施提供了见解。这项工作通过提供一种用于诊断和缓解T2I生成中偏见的综合工具，推动了该领域的发展，倡导更公平的AI系统。
英文摘要：
The transformative potential of text-to-image (T2I) models hinges on their ability to synthesize culturally diverse, photorealistic images from textual prompts. However, these models often perpetuate cultural biases embedded within their training data, leading to systemic misrepresentations. This paper benchmarks the Component Inclusion Score (CIS), a metric designed to evaluate the fidelity of image generation across cultural contexts. Through extensive analysis involving 2,400 images, we quantify biases in terms of compositional fragility and contextual misalignment, revealing significant performance gaps between Western and non-Western cultural prompts. Our findings underscore the impact of data imbalance, attention entropy, and embedding superposition on model fairness. By benchmarking models like Stable Diffusion with CIS, we provide insights into architectural and data-centric interventions for enhancing cultural inclusivity in AI-generated imagery. This work advances the field by offering a comprehensive tool for diagnosing and mitigating biases in T2I generation, advocating for more equitable AI systems.
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。
