发表机构
The University of Osaka; RIKEN Center for Computational Science（大阪大学; 理化学研究所计算科学中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究利用日本和歌山城公园的566条轨迹微调Llama-3.1-8B，实现49.1%的下一个兴趣点准确率，在样本不足场景泛化性强，为旅游轨迹预测提供了高保真行为模型及反事实分析基础。
AI 中文摘要
在旅游目的地评估流动性干预措施需要预测不同条件下的游客行为，传统方法效果不佳，因为游客决策高度依赖天气、疲劳等情境因素，而模型无法泛化到未观测场景。大型语言模型（LLMs）通过预训练编码了关于人类行为的常识知识，能够对情境依赖的决策进行推理，且其自然语言表示可灵活整合异构信息，为该问题提供了解决方案。对本地轨迹进行微调可将这种通用理解适配到目的地特定模式。我们使用日本和歌山城公园的566条轨迹验证了该方法，微调后的Llama-3.1-8B实现了49.1%的下一个兴趣点（POI）准确率，且在雨天等样本不足的场景中仍保持较强性能，证明了有效的泛化能力。这确立了LLMs作为情境依赖旅游预测的高保真行为模型，为流动性干预措施的反事实分析奠定了基础。
英文摘要
Evaluating mobility interventions at tourist destinations requires predicting visitor behavior under varying conditions. Traditional methods struggle because tourist decisions depend heavily on context like weather and fatigue, yet models cannot generalize to unobserved scenarios. Large Language Models offer a solution by encoding commonsense knowledge about human behavior from pretraining, enabling reasoning about context-dependent decisions, while natural language representation flexibly integrates heterogeneous information. Fine-tuning on local trajectories adapts this general understanding to destination-specific patterns. We validate this approach using 566 trajectories from Wakayama Castle Park, Japan. Our fine-tuned Llama-3.1-8B achieves 49.1% next POI accuracy and maintains strong performance on undersampled scenarios like rainy days, demonstrating effective generalization. This establishes LLMs as high-fidelity behavior models for context-dependent tourist prediction, providing groundwork for counterfactual analysis of mobility interventions.
Comments5 pages, 4 figures. Accepted at the 2nd Workshop on AI for Urban Planning (AI4UP) at AAAI-26, Singapore, January 2026
