发表机构
Nanjing University of Posts and Telecommunications; Arizona State University（南京邮电大学; 亚利桑那州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对短期观测下长期混沌时间序列预测难题，提出PAC-LLM框架，结合相空间特征与LLMs能力，在多组混沌系统实验中优于现有基线方法。
AI 中文摘要
混沌时间序列预测是一项极具挑战性的任务，原因在于其对初始条件敏感且长期具有不可预测性。传统方法通常依赖充足的时间轨迹来学习长期动态，这限制了其在仅能获取短期观测时的适用性。尽管近期的大语言模型（LLMs）在时间序列预测中展现出巨大潜力，但其时间表征并未明确适配混沌系统的相空间结构与非线性演化。为解决这些问题，我们提出PAC-LLM，一种由LLMs驱动的面向长期混沌时间序列预测的相空间感知自适应融合框架。PAC-LLM利用学习到的相空间特征与文本信息，充分发挥LLMs的时间序列预测能力。特别地，我们设计了辅助特征模块与门控加权机制，用于多变量耦合信息的融合与选择。在代表性混沌系统上开展的大量实验表明，我们的方法在短期与长期预测中均优于现有的微调及零样本基线方法。我们的 ablation study（ ablation研究）进一步验证了PAC-LLM各关键组件的有效性。
英文摘要
Chaotic time series forecasting is a challenging task due to its sensitivity to initial conditions and long-term unpredictability. Traditional methods typically rely on sufficient temporal trajectories to learn long-term dynamics, which limits their applicability when only short-term observations are available. While recent Large Language Models (LLMs) have shown great potential for time series forecasting, their temporal representations are not explicitly tailored to the phase-space structure and nonlinear evolution of chaotic systems. To address these issues, we propose PAC-LLM, a phase-space-aware adaptive fusion framework for long-term chaotic time series forecasting powered by LLMs. PAC-LLM leverages learned phase-space features and textual information to fully enable LLM's time series forecasting capacity. In particular, we design an auxiliary feature module and a gated weighting mechanism for multivariate coupling information fusion and selection. Extensive experiments on representative chaotic systems demonstrate that our method outperforms existing fine-tuned and zero-shot baselines in both short-term and long-term predictions. Our ablation study further confirms the effectiveness of each key component in PAC-LLM.
