多模态大语言模型可预测城市安全感知，但编码非中立的人口统计先验
Multimodal Large Language Models Predict Urban Safety Perception but Encode Non-Neutral Demographic Priors
AI总结：
该研究验证多模态大语言模型可规模化预测城市安全感知，但发现其存在非中立人口统计先验，不同性别、种族角色下的安全判断存在系统偏差。
摘要：
理解人们如何感知城市环境对包容性规划至关重要，但传统调查成本高昂且难以规模化。我们研究多模态大语言模型（MLLMs）能否从街景图像评估城市安全感知，同时考虑感知的观察者依赖性。使用Place Pulse 2.0数据集，我们在中立提示及由性别、年龄、种族或民族定义的社会人口角色下，评估56个城市中的四个开源和闭源MLLMs，还分析用于证明每个分类合理性的关键词。所有四个模型表现出相当的零样本能力，城市宏观F1分数为65%-69%，并保留有意义的跨城市差异。然而，它们系统性偏向“安全”类别，低估不安全情况，且压缩城市间差异。它们的解释汇聚于共享视觉词汇：维护、绿化、秩序和居住特征支持“安全”判断，而恶化、孤立、照明差和行人活动有限支持“不安全”判断。固定图像时，角色提示会产生显著且结构化的转变：所有模型中，女性角色比男性角色产生更多“不安全”分类；年龄效应取决于模型，尽管中年角色通常最接近中立；黑人/非裔美国人和美洲原住民角色常表现出最大偏差，而最接近的种族或民族匹配因模型而异。这些发现表明，MLLMs可提供城市安全感知的可扩展信号，但并非从人口统计中立的视角出发。
英文摘要：
Understanding how people perceive urban environments is essential for inclusive planning, yet conventional surveys are costly and difficult to scale. We investigate whether Multimodal Large Language Models (MLLMs) can assess perceived urban safety from street-view imagery while accounting for the observer-dependent nature of perception. Using Place Pulse 2.0, we evaluate four open and proprietary MLLMs across 56 cities under a Neutral prompt and socio-demographic personas defined by gender, age, and race or ethnicity. We also analyse the keywords generated to justify each classification. All four models display comparable zero-shot capability, with city-macro F1 scores of 65--69%, and preserve meaningful cross-city variation. However, they systematically favour the Safe class, underpredict unsafety, and compress differences between cities. Their explanations converge on a shared visual lexicon: maintenance, greenery, order, and residential character support Safe judgements, whereas deterioration, isolation, poor lighting, and limited pedestrian activity support Unsafe judgements. Persona prompting produces substantial and structured shifts while holding the image fixed. Female personas yield more Unsafe classifications than Male personas across all models; age effects are model-dependent, although Middle-aged personas generally remain closest to Neutral. Black/African American and Native American personas frequently show the largest departures, while the closest race or ethnicity match varies by model. These findings show that MLLMs can provide scalable signals of perceived urban safety, but not from a demographically neutral standpoint.
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。
