文化褪色处：揭示文生图模型中的文化鸿沟

摘要

多语言文本到图像生成模型在视觉真实性与语义对齐方面进展迅速，现已得到广泛应用。然而其输出结果会随文化语境产生差异：由于语言承载着文化内涵，基于多语言提示词生成的图像应当保持跨语言的文化一致性。我们通过系统性分析发现，当前T2I模型在处理多语言提示时往往产生文化中性或英语文化偏向的结果。对两个代表性模型的剖析表明，该问题并非源于文化知识的缺失，而是文化相关表征的激活不足所致。我们提出一种探测方法，可将文化敏感信号定位至少数固定层中的特定神经元集群。基于此发现，我们引入两种互补的对齐策略：（1）无需微调主干网络的推理时文化激活技术，通过放大已识别神经元的响应强度；（2）层定向文化增强方法，仅更新与文化相关的模型层。在自建CultureBench上的实验表明，该方法在保持生成质量与多样性的同时，相较强基线模型实现了文化一致性的持续提升。

English

Multilingual text-to-image (T2I) models have advanced rapidly in terms of visual realism and semantic alignment, and are now widely utilized. Yet outputs vary across cultural contexts: because language carries cultural connotations, images synthesized from multilingual prompts should preserve cross-lingual cultural consistency. We conduct a comprehensive analysis showing that current T2I models often produce culturally neutral or English-biased results under multilingual prompts. Analyses of two representative models indicate that the issue stems not from missing cultural knowledge but from insufficient activation of culture-related representations. We propose a probing method that localizes culture-sensitive signals to a small set of neurons in a few fixed layers. Guided by this finding, we introduce two complementary alignment strategies: (1) inference-time cultural activation that amplifies the identified neurons without backbone fine-tuned; and (2) layer-targeted cultural enhancement that updates only culturally relevant layers. Experiments on our CultureBench demonstrate consistent improvements over strong baselines in cultural consistency while preserving fidelity and diversity.

文化褪色处：揭示文生图模型中的文化鸿沟

Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation

摘要

Support