用大模型生成真实事件下的行人轨迹，更贴近现实。
ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
- 基于模糊痕迹理论提取习惯与事件的冲突逻辑
- 在台风、疫情、奥运三类事件中表现优于现有方法
- 首个带事件标注的轨迹数据集，适合城市研究者
人类移动生成旨在合成合理轨迹数据，广泛用于城市系统研究。尽管基于大语言模型的方法在生成日常轨迹方面表现优异，但在大规模社会事件期间的偏离移动行为建模上仍存在不足。这一局限源于两个关键缺口：(1) 缺乏用于设计与评估的事件标注移动数据集；(2) 当前框架无法在用户习惯模式与事件约束之间协调冲突决策。本文提出双重贡献：首先构建了首个涵盖台风“海贝思”、新冠疫情和2021年东京奥运会三类重大事件的事件标注移动数据集；其次提出ELLMob框架，基于模糊痕迹理论，先提取习惯模式与事件约束间的竞争理由，再通过迭代对齐生成兼具习惯基础与事件响应性的轨迹。大量实验表明，ELLMob在所有事件场景下均超越现有基线，验证了其有效性。代码与数据集已开源。
原文摘要 · Abstract (English)
Human mobility generation aims to synthesize plausible trajectory data, which is widely used in urban system research. While Large Language Model-based methods excel at generating routine trajectories, they struggle to capture deviated mobility during large-scale societal events. This limitation stems from two critical gaps: (1) the absence of event-annotated mobility datasets for design and evaluation, and (2) the inability of current frameworks to reconcile competitions between users' habitual patterns and event-imposed constraints when making trajectory decisions. This work addresses these gaps with a twofold contribution. First, we construct the first event-annotated mobility dataset covering three major events: Typhoon Hagibis, COVID-19, and the Tokyo 2021 Olympics. Second, we propose ELLMob, a self-aligned LLM framework that first extracts competing rationales between habitual patterns and event constraints, based on Fuzzy-Trace Theory, and then iteratively aligns them to generate trajectories that are both habitually grounded and event-responsive. Extensive experiments show that ELLMob wins state-of-the-art baselines across all events, demonstrating its effectiveness. Our codes and datasets are available at https://github.com/deepkashiwa20/ELLMob.
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。