用提示词重编程大模型，实现更准确的长期时间序列概率预测
PaP-NF: Probabilistic Long-Term Time Series Forecasting via Prefix-as-Prompt Reprogramming and Normalizing Flows
- 通过提示词机制将时间序列映射到冻结的大语言模型中
- 结合归一化流解码器，有效捕捉多模态不确定性，CRPS显著降低
- 适合需要评估预测置信度的金融、气象等长期预测场景
时间序列预测在众多实际应用中至关重要，现有方法多依赖确定性模型。然而真实世界未来行为具有内在不确定性和复杂性，单点预测难以满足需求。因此亟需能量化并表示不确定性的概率预测方法。本文提出PaP-NF框架，通过前缀作为提示（Prefix-as-Prompt）机制，将连续时间序列表示与冻结的大语言模型对齐，并以大模型提取的全局上下文作为归一化流解码器的条件输入。使用标准概率预测指标连续排名概率得分（CRPS）评估预测分布质量。在多个长期预测基准上，PaP-NF稳健地捕捉了多模态不确定性，同时保持了有竞争力的点预测精度。官方代码已开源：https://github.com/democracy04/PaP-NF
原文摘要 · Abstract (English)
Time series forecasting plays a central role in many real-world applications and has been extensively studied. Most existing approaches rely on deterministic models. However, real-world environments exhibit inherently uncertain and complex future behaviors, making single-point predictions insufficient. This highlights the need for probabilistic forecasting methods that can quantify and represent uncertainty. In this work, we propose PaP-NF, a probabilistic forecasting framework that aligns continuous time series representations with a frozen large language model (LLM) using a Prefix-as-Prompt mechanism, and conditions a normalizing flow decoder on the global context extracted by the LLM. The quality of the resulting predictive distributions is evaluated using the Continuous Ranked Probability Score (CRPS), a standard metric in probabilistic forecasting. Across a variety of long-term forecasting benchmarks, PaP-NF robustly captures multi-modal uncertainty while maintaining competitive point forecasting accuracy. The official implementation is available at: https://github.com/democracy04/PaP-NF
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。