DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework

TL;DR

This paper introduces DualSG, a dual-stream framework that leverages large language models as semantic guides to improve multivariate time series forecasting by providing explicit natural language summaries of trends.

Contribution

The paper proposes a novel dual-stream framework that uses LLMs as semantic guidance modules with explicit trend summaries, enhancing forecasting accuracy over existing methods.

Findings

DualSG outperforms 15 state-of-the-art baselines on real-world datasets.

Explicit semantic guidance improves forecasting interpretability and accuracy.

The caption-guided fusion module effectively models inter-variable relationships.

Abstract

Multivariate Time Series Forecasting plays a key role in many applications. Recent works have explored using Large Language Models for MTSF to take advantage of their reasoning abilities. However, many methods treat LLMs as end-to-end forecasters, which often leads to a loss of numerical precision and forces LLMs to handle patterns beyond their intended design. Alternatively, methods that attempt to align textual and time series modalities within latent space frequently encounter alignment difficulty. In this paper, we propose to treat LLMs not as standalone forecasters, but as semantic guidance modules within a dual-stream framework. We propose DualSG, a dual-stream framework that provides explicit semantic guidance, where LLMs act as Semantic Guides to refine rather than replace traditional predictions. As part of DualSG, we introduce Time Series Caption, an explicit prompt format that summarizes trend patterns in natural language and provides interpretable context for LLMs, rather than relying on implicit alignment between text and time series in the latent space. We also design a caption-guided fusion module that explicitly models inter-variable relationships while reducing noise and computation. Experiments on real-world datasets from diverse domains show that DualSG consistently outperforms 15 state-of-the-art baselines, demonstrating the value of explicitly combining numerical forecasting with semantic guidance.