研究人员开发了新的框架，以增强大型语言模型（LLM）在时间序列预测中的应用。PaP-NF 利用 Prefix-as-Prompt 机制将时间序列数据与冻结的 LLM 对齐，实现概率预测和不确定性量化。Time-Prompt 集成了可学习的软提示和文本化硬提示来指导 LLM，融合时间数据和文本数据以提高预测准确性。MAP4TS 虽然已撤回，但提出了一个多方面提示框架，将经典时间序列分析纳入提示设计，以提高 LLM 的性能。 AI
影响 新的基于LLM的框架为时间序列预测任务提供了更高的准确性和不确定性量化能力。
排序理由 多篇研究论文介绍了使用LLM进行时间序列预测的新颖框架。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2605.23219v1 Announce Type: cross Abstract: 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 an…
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 pr…
arXiv:2506.17631v4 Announce Type: replace-cross Abstract: Time series forecasting aims to model temporal dependencies among variables for future state inference, holding significant importance and widespread applications in real-world scenarios. Although deep learning-based metho…
arXiv:2510.23090v2 Announce Type: replace Abstract: Recent advances have investigated the use of pretrained large language models (LLMs) for time-series forecasting by aligning numerical inputs with LLM embedding spaces. However, existing multimodal approaches often overlook the …