Integrating adaptive human behavior into epidemic models with large language models
Artificial Intelligence
Summary
The authors created a new method called GABLE that uses large language models to predict how people change their behavior during epidemics, like COVID-19. Instead of relying on data like phone mobility, GABLE generates age-specific contact patterns that better reflect real human interactions during different stages of an outbreak. This approach helps improve short-term forecasts and can test how different policies might affect the spread of disease before they are put into place. Overall, the authors show that combining language models with disease models offers a flexible way to capture changing human behavior in epidemics.
Authors
Yicheng Mao, Haoyang Li, Rob Deardon, Hongru Du
Abstract
Infectious disease transmission is shaped by patterns of human interaction, which adapt as epidemic conditions change. Capturing these context-dependent behaviors remains a fundamental challenge for epidemic models. Here, we recast this challenge by using large language models (LLMs) to represent adaptive human behavior within mechanistic epidemic models. We operationalize this idea through Generative Adaptive Behavioral Layer for Epidemics (GABLE), which adapts LLMs to infer behavioral responses to epidemic and policy conditions and translates them into age-structured contact matrices coupled to a mechanistic epidemic model. Applied to COVID-19 in France, GABLE reproduced responses in population mixing and age-specific contact structures that remained epidemiologically informative. In short-term forecasting, LLM-generated contact matrices outperformed mobility-driven matrices derived from real-world mobility data, with the largest gains at longer horizons. GABLE also extends beyond forecasting to prospective policy evaluation by projecting behavioral and epidemic responses to candidate interventions before implementation. When supplied with subsequently implemented policies, GABLE reproduced epidemic trajectories and generated distinct responses to alternative policy timing and composition. By leveraging LLMs as a flexible behavioral layer, GABLE provides a framework for coupling context-sensitive behavioral generation with epidemic dynamics.