Metraipolis › archive › dc_b95b244f7274
LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting — arXiv:2510.20952
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2510.20952
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:10:56.022Z
- SHA-256 of the archived text
b9e1721ef51d8a58c2d1abaa5c1efc43d4cb2d68e292852199ec7c84cc42f6e6- Stable URL of this page
https://metraipolis.com/documento/dc_b95b244f7274
How to cite
LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting — arXiv:2510.20952 — arXiv (en), https://arxiv.org/abs/2510.20952 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b95b244f7274 (Metraipolis archive dc_b95b244f7274, sha256 b9e1721ef51d8a58c2d1abaa5c1efc43d4cb2d68e292852199ec7c84cc42f6e6)
BibTeX
@misc{dcb95b244f7274,
title = {LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting — arXiv:2510.20952},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2510.20952},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b95b244f7274; sha256 b9e1721ef51d8a58c2d1abaa5c1efc43d4cb2d68e292852199ec7c84cc42f6e6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2510.20952. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Forecasting in the real world requires integrating structured time-series data with unstructured textual information, but existing methods are architecturally limited by fixed input/output horizons and are unable to model or quantify uncertainty. We address this challenge by introducing LLM-integrated Bayesian State space models (LBS), a novel probabilistic framework for multimodal temporal forecasting. At a high level, LBS consists of two components: (1) a state space model (SSM) backbone that captures the temporal dynamics of latent states from which both numerical and textual observations are generated and (2) a pretrained large language model (LLM) that is adapted to encode textual inputs for posterior state estimation and decode textual forecasts consistent with the latent trajectory. This design enables flexible lookback and forecast windows, principled uncertainty quantification, and improved temporal generalization thanks to the well-suited inductive bias of SSMs toward modeling dynamical systems. Experiments on the TextTimeCorpus benchmark demonstrate that LBS improves the previous state-of-the-art by 13.20% while providing human-readable summaries of each forecast. Our work is the first to unify LLMs and SSMs for joint numerical and textual prediction, offering a novel foundation for multimodal temporal reasoning. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2510.20952 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T06:07:08.576Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).