T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation
This addresses the problem of time series forecasting for applications like infectious disease prediction, though it is incremental as it builds on existing LLM-based methods with a novel training approach.
The paper tackles the challenge of enabling large language models (LLMs) to forecast time series by proposing T-LLM, a temporal distillation framework that transfers predictive behavior from a lightweight temporal teacher during training, resulting in consistent outperformance of existing LLM-based methods across full-shot, few-shot, and zero-shot settings.
Time series forecasting plays a critical role in decision-making across many real-world applications. Unlike data in vision and language domains, time series data is inherently tied to the evolution of underlying processes and can only accumulate as real-world time progresses, limiting the effectiveness of scale-driven pretraining alone. This time-bound constraint poses a challenge for enabling large language models (LLMs) to acquire forecasting capability, as existing approaches primarily rely on representation-level alignment or inference-time temporal modules rather than explicitly teaching forecasting behavior to the LLM. We propose T-LLM, a temporal distillation framework that equips general-purpose LLMs with time series forecasting capability by transferring predictive behavior from a lightweight temporal teacher during training. The teacher combines trend modeling and frequency-domain analysis to provide structured temporal supervision, and is removed entirely at inference, leaving the LLM as the sole forecasting model. Experiments on benchmark datasets and infectious disease forecasting tasks demonstrate that T-LLM consistently outperforms existing LLM-based forecasting methods under full-shot, few-shot, and zero-shot settings, while enabling a simple and efficient deployment pipeline.