VISTA：视觉语言模型中的语义差异审计
VISTA: Auditing Semantic Divergence in Vision-Language Models
AI总结：
研究视觉语言模型中视觉概念条件性差异，提出VISTA黑箱跨模型审计方法，结合语义熵与基于分布的差异标记异常，通过实验验证其有效性并发现新差异模式。
摘要：
视觉语言模型可能表现出视觉概念条件性差异，文本审计方法无法检测。本文提出VISTA黑箱跨模型审计，结合语义熵与基于分布的差异来标记特定于模型的异常。通过微调植入概念条件立场并审计六个模型，发现高可疑案例及新差异模式。
英文摘要：
Vision-language models can exhibit visual concept-conditioned divergence: given images containing demographic features, corporate logos, or ideological symbols, some models produce unusually uniform responses that differ from what peer models say about the same input. These behaviors evade text-only audits because visual concepts cannot be isolated or substituted the way text tokens can. We present VISTA (Visual Inconsistency Screening Through Analysis), a black-box cross-model audit that couples semantic entropy with distribution-based divergence to flag model-specific anomalies. In a controlled study, we implant concept-conditioned stances in three VLMs via fine-tuning on small biased datasets and confirm that VISTA detects them. Auditing six VLMs across 19 topics, VISTA surfaces 142 high-suspicion cases (1.2%) and identifies selective refusal as a previously unreported divergence pattern, where models refuse demographic queries at rates varying from 0 to 65% across groups.
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。
