Projects per year
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 language | English |
|---|---|
| Title of host publication | CIKM '25 |
| Subtitle of host publication | Proceedings of the 34th ACM International Conference on Information and Knowledge Management |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 4498–4508 |
| Number of pages | 11 |
| ISBN (Electronic) | 9798400720406 |
| DOIs | |
| Publication status | Published - 11 Oct 2025 |
| Event | 34th ACM International Conference on Information and Knowledge Management - COEX, Seoul, Korea, Republic of Duration: 10 Nov 2025 → 14 Nov 2025 https://cikm2025.org/ |
Publication series
| Name | Proceedings of the ACM Conference on Information and Knowledge Management |
|---|---|
| Publisher | ACM |
| ISSN (Electronic) | 2155-0751 |
Conference
| Conference | 34th ACM International Conference on Information and Knowledge Management |
|---|---|
| Abbreviated title | CIKM '25 |
| Country/Territory | Korea, Republic of |
| City | Seoul |
| Period | 10/11/25 → 14/11/25 |
| 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.-
Adaptive Multi-Source Transfer Learning Approaches for Environmental Challenges
Wang, S. (Principal Investigator)
Engineering & Physical Science Research Council
1/03/24 → 28/02/26
Project: Research Councils
-
Data Stream Learning Under Uncertainty
Wang, S. (Principal Investigator)
1/10/22 → 1/04/26
Project: Industry
-
Baskerville 2.0: Enhanced Provision for High End and On-Demand Users
Styles, I. (Principal Investigator)
Engineering & Physical Science Research Council
4/01/22 → 3/05/22
Project: Research Councils
-
Baskerville: a national accelerated compute resource
Cai, B. (Co-Investigator) & Morris, A. (Principal Investigator)
Engineering & Physical Science Research Council, Lenovo UK Limited
13/10/20 → 31/03/25
Project: Research Councils