arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01801cs.LGcs.AIcs.CL
收藏

面向时间序列的大语言模型:综述

Large Language Models for Time Series: A Survey

University of California, San Diego(加利福尼亚大学圣迭戈分校)

Xiyuan Zhang, Ranak Roy Chowdhury, Rajesh K. Gupta, Jingbo Shang

AI总结:

本文综述了大语言模型用于时间序列分析的方法体系,涵盖直接提示、量化、对齐、视觉桥接和工具结合等策略,并梳理了多模态数据集与未来挑战。

摘要:

大语言模型(LLMs)已在自然语言处理和计算机视觉等领域得到广泛应用。超越文本、图像和图形,LLMs 在时间序列数据分析方面展现出巨大潜力,可惠及气候、物联网、医疗、交通、音频和金融等领域。本综述论文深入探讨并给出了利用 LLMs 能力进行时间序列分析的各种方法的详细分类体系。我们解决了弥合 LLMs 原始文本数据训练与时间序列数据数值特性之间差距这一固有挑战,并探索了将知识从 LLMs 迁移和蒸馏到数值时间序列分析的策略。我们详细介绍了多种方法,包括:(1)直接提示 LLMs,(2)时间序列量化,(3)对齐技术,(4)利用视觉模态作为桥接机制,以及(5)LLMs 与工具的结合。此外,本综述全面概述了现有多模态时间序列与文本数据集,并深入探讨了这一新兴领域面临的挑战和未来机遇。我们维护着一个持续更新的 Github 仓库,其中包含本综述所讨论的所有论文和数据集。

英文摘要:

Large Language Models (LLMs) have seen significant use in domains such as natural language processing and computer vision. Going beyond text, image and graphics, LLMs present a significant potential for analysis of time series data, benefiting domains such as climate, IoT, healthcare, traffic, audio and finance. This survey paper provides an in-depth exploration and a detailed taxonomy of the various methodologies employed to harness the power of LLMs for time series analysis. We address the inherent challenge of bridging the gap between LLMs' original text data training and the numerical nature of time series data, and explore strategies for transferring and distilling knowledge from LLMs to numerical time series analysis. We detail various methodologies, including (1) direct prompting of LLMs, (2) time series quantization, (3) aligning techniques, (4) utilization of the vision modality as a bridging mechanism, and (5) the combination of LLMs with tools. Additionally, this survey offers a comprehensive overview of the existing multimodal time series and text datasets and delves into the challenges and future opportunities of this emerging field. We maintain an up-to-date Github repository which includes all the papers and datasets discussed in the survey.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑