{"type":"ScholarlyArticle","title":"Speaking Numbers to LLMs: Multi-Wavelet Number Embeddings for Time Series Forecasting","authors":[{"name":"Defu Cao","slug":"defu-cao","given":"Defu","family":"Cao","affiliation":""},{"name":"Zijie Lei","slug":"zijie-lei","given":"Zijie","family":"Lei","affiliation":""},{"name":"Muyan Weng","slug":"muyan-weng","given":"Muyan","family":"Weng","affiliation":""},{"name":"Jiao Sun","slug":"jiao-sun","given":"Jiao","family":"Sun","affiliation":""},{"name":"Yan Liu","slug":"yan-liu","given":"Yan","family":"Liu","affiliation":""}],"abstract":"Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet their discrete, language-oriented tokenization and embedding interfaces are misaligned with continuous numerical values, often harming numerical ordering and forecasting reliability. We propose TempoWave, a plug-and-play temporal wavelet digit interface that maps each scalar observation into digit-wise embeddings constructed from multi-wavelet, multi-scale coefficients. By directly overriding standard token representations, TempoWave seamlessly exposes both fine-grained local fluctuations and macro global structures in a transformer-compatible form, ensuring that precise numerical formatting, distinct digit identity, and robustness to common normalization operations are maintained throughout the LLM pipeline. Experiments across five context-enriched forecasting benchmarks demonstrate that TempoWave consistently improves LLM-based forecasters over standard numeric tokenization and alternative embedding interfaces, achieving a new state-of-the-art. These results highlight the numeric interface as a key bottleneck and suggest that principled multi-resolution embeddings can better couple LLMs' contextual reasoning with precise forecasting. Our code is available at https://github.com/DC-research/TempoWAVE.","doi":"10.24963/ijcai.2026/464","url":"https://ijcai.org/proceedings/2026/464","pdf":"https://ijcai.org/proceedings/2026/0464.pdf","markdown":"https://ijcai.org/proceedings/2026/464.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/464","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":464,"pages":{"first":4170,"last":4178},"keywords":["Natural Language Processing: Language models","Machine Learning: Time series and data streams","Natural Language Processing: Embeddings"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}