arXiv 2606.161732026-06-16cs.AI

TimeVista：探索和利用视觉语言模型作为时间序列预测的评判者

TimeVista: Exploring and Exploiting Vision-Language Models as Judges for Time Series Forecasting

School of Software, BNRist, Tsinghua University（清华大学软件学院、北京信息科学与技术国家研究中心）

Zhi Chen, Yuxuan Wang, Jialong Wu, Yong Liu, Haoran Zhang, Xingjian Su, Jianmin Wang, Mingsheng Long

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出TimeVista框架，利用视觉语言模型（VLM）作为时间序列预测的评判者，通过微观和宏观判断结合上下文信息评估预测质量，实验表明VLM比传统指标更符合人类偏好。

摘要：

高质量的时间序列预测对于现实世界的决策至关重要。然而，传统的逐点度量往往无法揭示复杂的时间模式，并且与人类直观偏好的一致性较差。虽然“LLM-as-a-Judge”范式通过提供灵活、符合人类判断的评估彻底改变了文本评估，但其在时间序列中的应用仍鲜有探索。在本文中，我们利用视觉语言模型（VLM）作为时间序列预测的评判者，利用它们理解基于文本信息的时间序列图的能力。具体来说，我们提出了一种新颖的框架，整合了基于上下文信息的微观和宏观层面判断来评估时间序列预测。为此，我们引入了TimeVista，一个全面的VLM-as-a-Judge基准，包含5563个时间序列样本及其详细的评估标准。广泛的元评估表明，VLM是高度可靠的评判者，与人类偏好的一致性显著高于传统指标。基于我们的基准，我们在VLM-as-a-Judge范式下全面评估了近期的时间序列基础模型（TSFM）。我们的结果表明，VLM作为稳健且可解释的评判者，为评估时间序列模型提供了全面且符合人类的标准。

英文摘要：

High-quality time series forecasting is pivotal for real-world decision-making. However, traditional point-wise metrics often fail to reveal complex temporal patterns and align poorly with human intuitive preferences. While the ''LLM-as-a-Judge'' paradigm has revolutionized text evaluation by providing flexible, human-aligned judgment, its application to time series remains largely unexplored. In this paper, we leverage Vision-Language Models (VLMs) as judges for time series forecasting, harnessing their ability to comprehend time series plots grounded in textual information. Specifically, we propose a novel framework integrating micro- and macro-level judgments informed by contextual information to evaluate time series forecasting. To this end, we introduce TimeVista, a comprehensive VLM-as-a-Judge benchmark comprising 5563 time series samples paired with detailed evaluation rubrics. Extensive meta-evaluations demonstrate that VLMs are highly reliable judges, achieving significantly higher consistency with human preferences than conventional metrics. Building upon our benchmark, we comprehensively assess recent Time Series Foundation Models (TSFMs) under the VLM-as-a-Judge paradigm. Our results demonstrate that VLMs serve as robust and interpretable judges, providing a comprehensive, human-aligned standard for evaluating time series models.

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。