大型语言模型通过文化不平等的基线感知城市
Culturally uneven urban perception in large language models
AI总结：
本研究通过全球平衡的街景样本测试前沿LLM的城市感知，发现中性提示实际上偏向欧美文化，且文化提示能改变情感评价但无法恢复人类语义多样性。
摘要：
大型语言模型（LLM）越来越多地被用于描述、评估和解释地点，但目前尚不清楚它们是否从文化中立的立场出发。本文使用平衡的全球街景样本和保持中立或调用不同区域文化立场的提示，测试前沿LLM的城市感知。在开放式描述和结构化地点判断中，中性条件在实践中并非中立。与欧洲和北美相关的提示在系统上比许多非西方提示更接近基线，表明模型感知围绕文化不平等的参考框架而非通用框架组织。文化提示也改变了情感评价，对某些提示身份产生基于情感的群体内偏好。与区域人类文本-图像基准的比较表明，文化接近的提示可以改善与人类描述的一致性，但未能恢复人类水平的语义多样性，并且通常保留了情感提升的风格。同样的不对称性出现在安全性、美丽、财富、活力、无聊和抑郁的结构化判断中，模型输出是可解释的，但仅部分再现了人类群体差异。这些发现表明，LLM并非从虚无中感知城市：它们通过一个文化不平等的基线来感知，该基线塑造了什么是普通、熟悉和积极评价的。
英文摘要：
Large language models (LLMs) are increasingly used to describe and evaluate cities, yet the cultural structure of their urban judgments remains understudied. Here we introduce a measurement framework for testing whether LLM-based urban perception is culturally neutral, using a globally stratified street-view image dataset. Open-ended descriptions and structured scores generated by three frontier multimodal models all show that the neutral baseline lies closer to regional framings associated with Europe and North America than to other cultural framings. Comparisons between AI and human urban perception further show that prompting can move AI responses closer to specific regional human descriptions, but fails to recover the variety and diversity of human responses, flattening observed demographic patterns and introducing sentiment-based self-favouring bias. These results indicate a systematic risk in treating AI as a neutral tool for urban tasks, especially when model outputs are used to compare, evaluate or represent cities across cultural contexts.
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。
