对齐却刻板？系统提示对基于LVLM的文生图模型社会偏见的隐性影响

摘要

基于大规模视觉语言模型（LVLM）的文生图（T2I）系统已成为图像生成的主流范式，但其是否会放大社会偏见仍缺乏深入研究。本文揭示，基于LVLM的模型比非LVLM模型产生明显更具社会偏见的图像。我们构建了一个包含四个语言复杂度层级、涵盖1024个提示词的基准测试集，系统评估了多维度人口统计特征的偏差。分析发现，引导LVLM的预定义系统提示词是产生偏见行为的主要诱因。通过解码中间表征、词元概率诊断和嵌入关联分析，我们揭示了系统提示词如何编码人口统计先验信息并传导至图像合成过程。为此，我们提出FairPro——一种免训练的元提示框架，使LVLM能够在测试阶段实现自我审查并构建具有公平意识的系统提示词。在SANA和Qwen-Image两个LVLM基T2I模型上的实验表明，FairPro在保持图文对齐度的同时显著降低了人口统计偏差。本研究不仅揭示了系统提示词在偏见传播中的核心作用，更为构建更具社会责任的T2I系统提供了可部署的实用方案。

English

Large vision-language model (LVLM) based text-to-image (T2I) systems have become the dominant paradigm in image generation, yet whether they amplify social biases remains insufficiently understood. In this paper, we show that LVLM-based models produce markedly more socially biased images than non-LVLM-based models. We introduce a 1,024 prompt benchmark spanning four levels of linguistic complexity and evaluate demographic bias across multiple attributes in a systematic manner. Our analysis identifies system prompts, the predefined instructions guiding LVLMs, as a primary driver of biased behavior. Through decoded intermediate representations, token-probability diagnostics, and embedding-association analyses, we reveal how system prompts encode demographic priors that propagate into image synthesis. To this end, we propose FairPro, a training-free meta-prompting framework that enables LVLMs to self-audit and construct fairness-aware system prompts at test time. Experiments on two LVLM-based T2I models, SANA and Qwen-Image, show that FairPro substantially reduces demographic bias while preserving text-image alignment. We believe our findings provide deeper insight into the central role of system prompts in bias propagation and offer a practical, deployable approach for building more socially responsible T2I systems.

对齐却刻板？系统提示对基于LVLM的文生图模型社会偏见的隐性影响

Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models

摘要

Support