An Infectious Disease Spread Simulation Based on Large Language Model Decision Making

Yonchanok Khaokaew, Ruochen Kong, Andreas Züfle, Hao Xue, Taylor Anderson, Chandini Raina MacIntyre, Matthew Scotch, Flora D. Salim, David J Heslop

Keywords: simulation; LLMs; epidemiology

Abstract: Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective public health interventions. Prior work has shown that large language models (LLMs) can simulate realistic human behaviour by generating decisions for digital twin agents based on demographic prompts and situational context. We build on this foundation with a spatially grounded agent-based simulation framework that integrates LLM-generated decisions about self-reporting influenza-like illness across a census-based synthetic population of agents. Location is treated as a central feature: agents are assigned to spatial units within cities, capturing spatial distributions of different demographic groups based on real-world census data, enabling geographically diverse behavioural modelling. We implement and compare three decision scenarios—independent reasoning, household influence, and message framing—and simulate self-reporting outcomes in San Francisco and Atlanta. Results reveal spatial variation in reporting rates, with significant effects from demographic factors, including income and education. Our framework generates synthetic data that captures both social and geographic heterogeneity, supporting spatial epidemiological modelling and bias-aware behavioural analysis.

Area: Modelling and Simluation of Societies (SIM)

Generative A I: I acknowledge that I have read and will follow this policy.

Submission Number: 1828