Work

From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs

Year: 2025

Type: conference-paper

Abstract: Evacuation decision prediction is critical for efficient and effective wildfire response by helping emergency management anticipate traffic congestion and bottlenecks, allocate resources, and minimize negative impacts.Traditional statistical methods for evacuation decision prediction fail to capture the complex and diverse behavioral logic of different individuals.In this work, for the first time, we introduce FLARE, short for facilitating LLM for advanced reasoning on wildfire evacuation decision prediction, a Large Language Model (LLM)-based framework that integrates behavioral theories and models to streamline the Chain-of-Thought (CoT) reasoning and subsequently integrate with memory-based Reinforcement Learning (RL) module to provide accurate evacuation decision prediction and understanding.Our proposed method addresses the limitations of using existing LLMs for evacuation behavioral predictions, such as limited survey data, mismatching with behavioral theory, conflicting individual preferences, implicit and complex mental states, and intractable mental statebehavior mapping.Experiments on three postwildfire survey datasets show an average of 20.47% performance improvement over traditional theory-informed behavioral models, with strong cross-event generalizability.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2025.acl-long.1438

Authors: Ruxiao Chen, Chenguang Wang, Yuran Sun, Xilei Zhao, Susu Xu

Institutions: Johns Hopkins University, University of Florida

Language: English

Topic: Evacuation and Crowd Dynamics

Subfield: Ocean Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, U.S. Department of Transportation

Awards: CLIMA/Collaborative Research: Riders on the Storm: Climate Adaptation of Housing Infrastructure for Resilient Communities in Coastal Cities, CAREER: Open-source Probabilistic AI Infrastructure for Dynamic Cascading Disaster Impacts Modeling and Assessment, A Clearinghouse on Natural Hazards Applications, CAREER: An Integrated Trustworthy AI Research and Education Framework for Modeling Human Behavior in Climate Disasters