用大模型预测游客行为，能准确应对下雨等特殊场景。
Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data
- 用预训练大模型+本地轨迹数据微调，结合上下文推理游客动向
- 在566条日本和歌山城公园轨迹上达49.1%的下一站景点预测准确率
- 特别擅长处理少样本场景，适合做旅游管理干预的模拟分析
评估旅游地出行干预效果需要预测游客在不同条件下的行为。传统方法因难以捕捉天气、疲劳等上下文因素而表现不佳，且无法推广到未观测情境。大语言模型通过预训练获得人类行为常识，可进行上下文依赖决策推理，并以自然语言形式灵活融合异构信息。对本地轨迹数据进行微调后，可将通用理解适配至特定目的地。我们在日本和歌山城公园使用566条轨迹验证该方法，微调后的Llama-3.1-8B模型达到49.1%的下一站兴趣点（next POI）预测准确率，且在雨天等低频场景下仍保持良好性能，证明其具备强泛化能力。这为基于上下文的游客行为建模提供了高保真工具，可用于出行干预的反事实分析。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。