ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework

2026-03-09

AI Summary

This study addresses the challenge that current large language models struggle to capture anomalous human mobility patterns during large-scale societal events—such as typhoons, pandemics, and the Olympics—due to the scarcity of event-annotated data and limited capacity to model the interplay between routine habits and event-induced constraints. To bridge this gap, the authors construct the first large-scale human mobility dataset with real-world major event annotations and propose a fuzzy-trace-theory-inspired self-aligned large language model framework. This framework iteratively aligns decision rationales underlying habitual and event-driven behaviors to generate event-aware trajectories. Evaluated across three real-world event scenarios, the method significantly outperforms existing baselines, producing trajectories that are both habitually plausible and responsive to event dynamics. The code and dataset are publicly released.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• human mobility generation
• large-scale societal events
• event-annotated dataset
• habitual patterns
• event constraints

Innovation

• event-driven mobility
• self-aligned LLM
• Fuzzy-Trace Theory
• trajectory generation
• event-annotated dataset