BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting

  • Shiqiao Zhou
  • , Holger Schöner
  • , Huanbo Lyu
  • , Edouard Fouché
  • , Shuo Wang*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

38 Downloads (Pure)

Abstract

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.
Original languageEnglish
Title of host publicationCIKM '25
Subtitle of host publicationProceedings of the 34th ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery (ACM)
Pages4498–4508
Number of pages11
ISBN (Electronic)9798400720406
DOIs
Publication statusPublished - 11 Oct 2025
Event34th ACM International Conference on Information and Knowledge Management - COEX, Seoul, Korea, Republic of
Duration: 10 Nov 202514 Nov 2025
https://cikm2025.org/

Publication series

NameProceedings of the ACM Conference on Information and Knowledge Management
PublisherACM
ISSN (Electronic)2155-0751

Conference

Conference34th ACM International Conference on Information and Knowledge Management
Abbreviated titleCIKM '25
Country/TerritoryKorea, Republic of
CitySeoul
Period10/11/2514/11/25
Internet address

Fingerprint

Dive into the research topics of 'BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting'. Together they form a unique fingerprint.

Cite this