BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting
By: Shiqiao Zhou , Holger Schöner , Huanbo Lyu and more
Potential Business Impact:
Helps predict future events using text and numbers.
Time series forecasting is a long-standing and highly challenging research topic. Recently, driven by the rise of large language models (LLMs), research has increasingly shifted from purely time series methods toward harnessing textual modalities to enhance forecasting performance. However, the vast discrepancy between text and temporal data often leads current multimodal architectures to over-emphasise one modality while neglecting the other, resulting in information loss that harms forecasting performance. To address this modality imbalance, we introduce BALM-TSF (Balanced Multimodal Alignment for LLM-Based Time Series Forecasting), a lightweight time series forecasting framework that maintains balance between the two modalities. Specifically, raw time series are processed by the time series encoder, while descriptive statistics of raw time series are fed to an LLM with learnable prompt, producing compact textual embeddings. To ensure balanced cross-modal context alignment of time series and textual embeddings, a simple yet effective scaling strategy combined with a contrastive objective then maps these textual embeddings into the latent space of the time series embeddings. Finally, the aligned textual semantic embeddings and time series embeddings are together integrated for forecasting. Extensive experiments on standard benchmarks show that, with minimal trainable parameters, BALM-TSF achieves state-of-the-art performance in both long-term and few-shot forecasting, confirming its ability to harness complementary information from text and time series. Code is available at https://github.com/ShiqiaoZhou/BALM-TSF.
Similar Papers
T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion
Machine Learning (CS)
Predicts future trends better by understanding patterns.
Integrating Time Series into LLMs via Multi-layer Steerable Embedding Fusion for Enhanced Forecasting
Artificial Intelligence
Helps computers predict future events better.
ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Data
Machine Learning (CS)
Predicts future events better using words and numbers.