T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation

TL;DR

T-LLM introduces a novel training framework that teaches large language models to forecast time series by distilling knowledge from a specialized temporal teacher, improving accuracy across various scenarios.

Contribution

The paper presents T-LLM, a new temporal distillation method that explicitly trains LLMs for time series forecasting, addressing limitations of previous approaches.

Findings

Outperforms existing LLM-based forecasting methods

Effective in full-shot, few-shot, and zero-shot settings

Enables simple and efficient deployment

Abstract

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.