ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
This work is significant for urban system researchers and planners, providing a more accurate method for synthesizing human mobility data, especially during critical societal events, which is an incremental improvement over existing LLM methods.
This paper tackles the problem of generating human mobility data that accurately reflects deviations caused by large-scale societal events, a limitation of existing LLM-based methods. The authors created the first event-annotated mobility dataset and developed ELLMob, a self-aligned LLM framework, which outperforms state-of-the-art baselines across three major events.
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.