用文本转换让大模型零样本预测多变量时间序列，效果超越主流方法。
Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecasting
- 将时序数据转为文本，结合分解与轻量提示策略提升预测能力。
- 在Llama 2 7B等小模型上表现优于现有基线，多变量预测精度显著提升。
- 适合无标签数据或快速部署的场景，尤其适合缺乏训练资源的研究者。
时间序列预测在众多动态系统中至关重要。尽管近期研究尝试利用大语言模型（LLMs）凭借其强泛化能力实现零样本预测，但其在复杂、噪声大且多变量时间序列上的表现仍不清晰。为此，本文提出LLMPred，通过将时序序列转化为文本并输入到LLM中进行零样本预测，结合两项关键预处理技术：首先对时序序列进行分解以提升复杂和含噪单变量序列的预测准确性；其次采用轻量级提示处理策略，将单变量预测能力拓展至多变量数据。在Llama 2 7B、Llama 3.2 3B、GPT-4o-mini、DeepSeek 7B等小型LLM上的大量实验表明，LLMPred在性能上达到或超越当前最优基线。充分的消融实验验证了各组件的有效性。
原文摘要 · Abstract (English)
Time-series prediction or forecasting is critical across many real-world dynamic systems, and recent studies have proposed using Large Language Models (LLMs) for this task due to their strong generalization capabilities and ability to perform well without extensive pre-training. However, their effectiveness in handling complex, noisy, and multivariate time-series data remains underexplored. To address this, we propose LLMPred which enhances LLM-based time-series prediction by converting time-series sequences into text and feeding them to LLMs for zero shot prediction along with two main data pre-processing techniques. First, we apply time-series sequence decomposition to facilitate accurate prediction on complex and noisy univariate sequences. Second, we extend this univariate prediction capability to multivariate data using a lightweight prompt-processing strategy. Extensive experiments with smaller LLMs such as Llama 2 7B, Llama 3.2 3B, GPT-4o-mini, and DeepSeek 7B demonstrate that LLMPred achieves competitive or superior performance compared to state-of-the-art baselines. Additionally, a thorough ablation study highlights the importance of the key components proposed in LLMPred.
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。