cs.LG提交于 2026-10-31已译

LLM 集成的贝叶斯状态空间模型用于多模态时间序列预测

LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting

Sungjun Cho · Changho Shin · Suenggwan Jo · Xinya Yan · Shourjo Aditya Chaudhuri · Frederic Sala

中文摘要

现实世界中的预测需要将结构化时间序列数据与非结构化文本信息相结合，但现有方法在架构上受限于固定的输入/输出窗口，且无法建模或量化不确定性。为此，提出 LLM 集成的贝叶斯状态空间模型（LBS），一种用于多模态时序预测的新型概率框架。LBS 由两部分组成：(1) 状态空间模型（SSM）主干，用于捕捉潜在状态的时间动态，数值和文本观测均由这些状态生成；(2) 预训练大语言模型（LLM），经适配后编码文本输入以进行后验状态估计，并解码与潜在轨迹一致的文本预测。该设计支持灵活的回看与预测窗口、有原则的不确定性量化，并因 SSM 对动力系统建模的归纳偏置而提升时间泛化能力。在 TextTimeCorpus 基准上的实验表明，LBS 较此前最优方法提升 13.20%，同时为每次预测提供人类可读的摘要。该工作是首个统一 LLM 与 SSM 进行数值与文本联合预测的研究，为多模态时序推理提供了新基础。

关键要点

01现有方法受限于固定输入/输出窗口，且无法建模或量化不确定性
02LBS 由 SSM 主干与适配的预训练 LLM 组成，分别负责状态动态与文本编解码
03在 TextTimeCorpus 上较此前最优提升 13.20%，并输出人类可读的预测摘要
04首次统一 LLM 与 SSM 实现数值与文本联合预测，支持灵活窗口与不确定性量化

解读

尚无解读。

原始英文摘要

arXiv:2510.20952v1 Announce Type: cross Abstract: 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.