稳定行为，有限变化：城市情感感知中LLM智能体的角色有效性
Stable Behavior, Limited Variation: Persona Validity in LLM Agents for Urban Sentiment Perception
AI总结：
研究通过多角色提示生成LLM智能体，发现角色内行为稳定但角色间差异有限，且无角色模型在某些任务中表现更优。
摘要：
大型语言模型（LLM）越来越多地被用作城市分析中人类感知的代理，但尚不清楚角色提示是否会产生有意义且可重复的行为多样性。我们研究了不同角色是否影响多模态LLM生成的城市情感判断。使用涵盖性别、经济状况、政治取向和人格的角色因子集，我们为每个角色实例化多个智能体，以评估来自PerceptSent数据集的城市场景图像，并评估角色内一致性和角色间变化。结果显示，共享角色的智能体之间存在强收敛性，表明行为稳定且可重复。然而，角色间分化有限：经济状况和人格引起统计上可检测但实际变化不大的影响，而性别没有可测量的效果，政治取向的影响可忽略不计。智能体还表现出极端偏差，压缩了人类注释中常见的中间情感类别。因此，在粗粒度极性任务上表现强劲，但随着情感分辨率的提高而下降，表明简单的基于标签的角色提示无法捕捉细粒度的感知判断。为了隔离角色条件的作用，我们还评估了没有角色的相同模型。令人惊讶的是，无角色模型在所有任务变体上与人类标签的一致性有时达到或超过有角色条件，表明在这种设置下，简单的基于标签的角色提示可能增加有限的注释价值。
英文摘要：
Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting produces meaningful and reproducible behavioral diversity. We investigate whether distinct personas influence urban sentiment judgments generated by multimodal LLMs. Using a factorial set of personas spanning gender, economic status, political orientation, and personality, we instantiate multiple agents per persona to evaluate urban scene images from the PerceptSent dataset and assess both within-persona consistency and cross-persona variation. Results show strong convergence among agents sharing a persona, indicating stable and reproducible behavior. However, cross-persona differentiation is limited: economic status and personality induce statistically detectable but practically modest variation, while gender shows no measurable effect and political orientation only negligible impact. Agents also exhibit an extremity bias, collapsing intermediate sentiment categories common in human annotations. As a result, performance remains strong on coarse-grained polarity tasks but degrades as sentiment resolution increases, suggesting that simple label-based persona prompting does not capture fine-grained perceptual judgments. To isolate the contribution of persona conditioning, we additionally evaluate the same model without personas. Surprisingly, the no-persona model sometimes matches or exceeds persona-conditioned agreement with human labels across all task variants, suggesting that simple label-based persona prompting may add limited annotation value in this setting.
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。
