LLM生成图像时会隐含性别种族偏见，新方法可无损改写提示减轻偏见
Aligned but Stereotypical? How System Prompts Shape Demographic Bias in LLM-Based Text-to-Image Models
- 通过系统提示分析发现LLM会引入隐性人口统计偏见
- 八款主流模型中基于LLM的均表现出更强的性别/种族偏向
- 提出FairPro框架，在不改变用户意图前提下减少偏见
文本到图像（T2I）系统越来越多地采用大语言模型（LLM）进行文本条件建模以理解并扩展用户提示。尽管这提升了提示理解与图文对齐能力，但我们发现即使未明确指定人口属性，该机制仍可能引入隐性的身份假设。为系统研究不同提示模糊度与复杂度下的行为差异，我们构建了一个涵盖多种提示场景的综合性基准。在八款近期T2I模型上的评估显示，基于LLM的系统始终表现出比非LLM基线更强的人口统计偏差。进一步分析表明，专属于基于LLM的T2I系统的系统提示（system prompts）显著影响文本嵌入，进而导致生成图像的偏见。基于此发现，我们提出FairPro——一种无需训练的去偏框架，能自适应生成兼顾公平性的指令，同时保持用户意图。实验表明，FairPro能显著降低人口统计差异，同时维持提示保真度。
原文摘要 · Abstract (English)
Text-to-image (T2I) systems increasingly rely on Large Language Model (LLM)-based text conditioning to interpret and expand user prompts. While this improves prompt understanding and text-image alignment, we find that it can also introduce implicit demographic assumptions, even when demographic attributes are unspecified. To systematically investigate this behavior across varying levels of prompt ambiguity and complexity, we construct a comprehensive benchmark covering diverse prompt settings. Evaluations on eight recent T2I models show that LLM-based systems consistently exhibit stronger demographic skew than non-LLM-based baselines. We further analyze system prompts, a component unique to LLM-based T2I systems that guides prompt interpretation and expansion. Our analyses show that these instructions strongly influence text embeddings, which subsequently leads to biased image generations. Motivated by these findings, we propose FairPro, a training-free debiasing framework that adaptively generates fairness-aware instructions while preserving user intent. Experiments demonstrate that FairPro substantially reduces demographic disparities while maintaining prompt fidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。