Semantics-Enhanced Retrieval-Augmented Time Series Forecasting

Title: Semantics-Enhanced Retrieval-Augmented Time Series Forecasting 标题： 语义增强的检索增强时间序列预测

Abstract: Time series forecasting models often benefit from historical patterns. Inspired by Retrieval-Augmented Generation (RAG), recent research explored retrieving relevant historical time series segments to enhance forecasting. However, relying solely on time series similarity is often insufficient for retrieval under non-stationarity. 摘要： 时间序列预测模型通常受益于历史模式。受检索增强生成（RAG）的启发，近期研究探索了通过检索相关的历史时间序列片段来增强预测效果。然而，在非平稳性条件下，仅依赖时间序列的相似性往往不足以进行有效的检索。

To address this, we propose a multimodal approach: a Semantics-Enhanced Retrieval-Augmented Time Series Forecasting framework, SERAF. Unlike mainstream approaches that depend only on time series similarity, SERAF conducts dual retrieval over the time series and their self-generated textual descriptions. It retrieves two complementary sets of historical patterns and corresponding futures, which are selectively and jointly used to guide future predictions. 为了解决这一问题，我们提出了一种多模态方法：语义增强的检索增强时间序列预测框架（SERAF）。与仅依赖时间序列相似性的主流方法不同，SERAF 对时间序列及其自生成的文本描述进行双重检索。它检索两组互补的历史模式及相应的未来数据，并将这些信息选择性地联合使用，以指导未来的预测。

Experiments across seven real-world datasets demonstrate the effectiveness of SERAF in bridging numerical and semantic views of time series compared with state-of-the-art baselines. 在七个真实世界数据集上的实验表明，与当前最先进的基准模型相比，SERAF 在连接时间序列的数值视图与语义视图方面表现出了显著的有效性。

---

Paper Details:

• Authors: Shiqiao Zhou, Zipeng Wu, Holger Schöner, Edouard Fouché, IAG Wilson, Shuo Wang
• arXiv ID: 2606.14941
• Date: 12 Jun 2026
• Subject: Artificial Intelligence (cs.AI)

论文详情：

• 作者： Shiqiao Zhou, Zipeng Wu, Holger Schöner, Edouard Fouché, IAG Wilson, Shuo Wang
• arXiv ID: 2606.14941
• 日期： 2026年6月12日
• 学科： 人工智能 (cs.AI)