Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper addresses the problem of poor generalization in hurricane evacuation prediction models across different geographic locations, identifying that households with similar characteristics exhibit systematically different decision patterns across states. To overcome this, they introduce Population-Adaptive Symbolic Mixture-of-Experts (PASM), which uses LLM-guided symbolic regression to discover human-readable decision rules and specializes them to data-driven subpopulations within a mixture-of-experts framework. PASM achieves significantly improved cross-location generalization performance compared to XGBoost, TabPFN, GPT-3.5-mini, and meta-learning baselines, while maintaining interpretability and fairness.
Hurricane evacuation decisions aren't universal: a model that works in Texas could fail in Florida because people with similar characteristics make systematically different choices based on location.
Accurate prediction of evacuation behavior is critical for disaster preparedness, yet models trained in one region often fail elsewhere. Using a multi-state hurricane evacuation survey, we show this failure goes beyond feature distribution shift: households with similar characteristics follow systematically different decision patterns across states. As a result, single global models overfit dominant responses, misrepresent vulnerable subpopulations, and generalize poorly across locations. We propose Population-Adaptive Symbolic Mixture-of-Experts (PASM), which pairs large language model guided symbolic regression with a mixture-of-experts architecture. PASM discovers human-readable closed-form decision rules, specializes them to data-driven subpopulations, and routes each input to the appropriate expert at inference time. On Hurricanes Harvey and Irma data, transferring from Florida and Texas to Georgia with 100 calibration samples, PASM achieves a Matthews correlation coefficient of 0.607, compared to XGBoost (0.404), TabPFN (0.333), GPT-5-mini (0.434), and meta-learning baselines MAML and Prototypical Networks (MCC $\leq$ 0.346). The routing mechanism assigns distinct formula archetypes to subpopulations, so the resulting behavioral profiles are directly interpretable. A fairness audit across four demographic axes finds no statistically significant disparities after Bonferroni correction. PASM closes more than half the cross-location generalization gap while keeping decision rules transparent enough for real-world emergency planning.