用简单提示词让大模型精准预测时间序列，无需大量训练。
Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition
- 将时间序列分块并分解，用提示词引导大模型理解模式。
- 在多个数据集上实现比传统方法更优的预测准确率。
- 适合希望快速部署大模型做时序预测的研究者与工程师。
大语言模型在时间序列分析中展现出新潜力，但以往工作常需大量微调且忽略序列间关联。本文探索无需复杂外部架构、也无需大规模重训练的简单提示策略。通过时间序列分解、分块标记和基于相似性的邻近增强等提示方法，显著提升大模型的预测质量。为此提出PatchInstruct方法，可在极简预处理下实现高精度预测，在多个基准数据集上表现优异，验证了纯提示策略的有效性。
原文摘要 · Abstract (English)
Recent advances in Large Language Models (LLMs) have demonstrated new possibilities for accurate and efficient time series analysis, but prior work often required heavy fine-tuning and/or ignored inter-series correlations. In this work, we explore simple and flexible prompt-based strategies that enable LLMs to perform time series forecasting without extensive retraining or the use of a complex external architecture. Through the exploration of specialized prompting methods that leverage time series decomposition, patch-based tokenization, and similarity-based neighbor augmentation, we find that it is possible to enhance LLM forecasting quality while maintaining simplicity and requiring minimal preprocessing of data. To this end, we propose our own method, PatchInstruct, which enables LLMs to make precise and effective predictions.
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。