EpiLLM: Unlocking the Potential of Large Language Models in Epidemic Forecasting

TL;DR

EpiLLM is a novel large language model framework designed specifically for epidemic forecasting, integrating spatio-temporal data and prompt learning to improve accuracy in predicting disease spread.

Contribution

The paper introduces EpiLLM, a dual-branch LLM architecture with spatio-temporal prompts and autoregressive modeling tailored for epidemic forecasting tasks.

Findings

EpiLLM outperforms existing baselines on COVID-19 datasets.

EpiLLM demonstrates effective scaling behavior.

The framework enhances epidemic prediction accuracy.

Abstract

Advanced epidemic forecasting is critical for enabling precision containment strategies, highlighting its strategic importance for public health security. While recent advances in Large Language Models (LLMs) have demonstrated effectiveness as foundation models for domain-specific tasks, their potential for epidemic forecasting remains largely unexplored. In this paper, we introduce EpiLLM, a novel LLM-based framework tailored for spatio-temporal epidemic forecasting. Considering the key factors in real-world epidemic transmission: infection cases and human mobility, we introduce a dual-branch architecture to achieve fine-grained token-level alignment between such complex epidemic patterns and language tokens for LLM adaptation. To unleash the multi-step forecasting and generalization potential of LLM architectures, we propose an autoregressive modeling paradigm that reformulates the epidemic forecasting task into next-token prediction. To further enhance LLM perception of epidemics, we introduce spatio-temporal prompt learning techniques, which strengthen forecasting capabilities from a data-driven perspective. Extensive experiments show that EpiLLM significantly outperforms existing baselines on real-world COVID-19 datasets and exhibits scaling behavior characteristic of LLMs.