GABLE epidemic model with LLMs
Integrating adaptive human behavior into epidemic models with large language models
GABLE offers more accurate epidemic forecasts than mobility data methods and can evaluate policy impacts before implementation, useful for public health planning.
Researchers developed GABLE, a Generative Adaptive Behavioral Layer for Epidemics, that uses large language models to represent adaptive human behavior in epidemic models.
Applied to COVID-19 in France, GABLE reproduced responses in population mixing and age-specific contact structures that remained epidemiologically informative.
LLM-generated contact matrices outperformed mobility-driven matrices from real-world data, with larger gains at longer forecasting horizons.
GABLE also enables prospective policy evaluation by projecting behavioral and epidemic responses to candidate interventions before implementation.
Integrating adaptive human behavior into epidemic models with large language models
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.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include GABLE, LLM, COVID-19, predictive models.
Source attribution: curated from arXiv cs.AI (@Yicheng Mao, Haoyang Li, Rob Deardon, Hongru Du).
