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

2025-05-19

AI Summary

Existing spatiotemporal epidemiological forecasting methods suffer from limited prediction accuracy and poor generalization across regions and time horizons. Method: We propose the first large language model (LLM) framework specifically designed for this task. It features: (1) a novel dual-branch architecture enabling fine-grained alignment between epidemic spatiotemporal patterns and linguistic tokens; (2) joint encoding of case counts and human mobility data, reformulating forecasting as an autoregressive language modeling problem; and (3) a spatiotemporal prompt learning mechanism to enhance the LLM’s awareness of epidemic dynamics. Contribution/Results: We are the first to demonstrate the scalability of LLMs for multi-step epidemiological forecasting. On real-world COVID-19 datasets, our method significantly outperforms state-of-the-art approaches, exhibiting canonical large-model scaling behavior and strong cross-regional generalization capability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Exploring LLMs' potential for epidemic forecasting
• Aligning epidemic patterns with LLM token adaptation
• Enhancing LLM perception via spatio-temporal prompts

Innovation

• Dual-branch architecture aligns epidemic patterns with tokens
• Autoregressive modeling transforms forecasting into token prediction
• Spatio-temporal prompt learning enhances epidemic perception