arXiv 2602.231612026-02cs.AI

PATRA: 面向时间序列问答的模式感知对齐与平衡推理

PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering

East China Normal University, Shanghai, China（华东师范大学）；Aalborg University, Aalborg, Denmark（奥胡斯大学）

Junkai Lu, Peng Chen, Xingjian Wu, Yang Shu, Chenjuan Guo, Christian S. Jensen, Bin Yang

备注：: Accepted By ICML 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有LLM方法在时间序列推理中忽略模式提取和简单任务主导学习的问题，提出模式感知对齐与平衡推理模型PATRA，通过提取趋势和季节模式实现深度对齐，并设计任务感知平衡奖励以协调不同难度任务的学习，在多种时间序列问答任务中优于强基线。

摘要：

时间序列推理既需要感知复杂动态，也需要逻辑深度。然而，现有的基于LLM的方法存在两个局限性：它们通常仅将时间序列视为文本或图像，未能捕捉回答特定问题所需的趋势和季节性等模式；并且当在简单和复杂任务的混合数据上训练时，较简单的目标往往主导学习过程，阻碍深层推理能力的发展。为解决这些局限性，我们提出了模式感知对齐与平衡推理模型（PATRA），引入了一种模式感知机制，从时间序列中提取趋势和季节性模式以实现深度对齐。此外，我们设计了一种任务感知的平衡奖励，以协调不同难度任务之间的学习，激励生成连贯的思维链。大量实验表明，PATRA在多种时间序列问答（TSQA）任务中优于强基线，展示了卓越的跨模态理解和推理能力。

英文摘要：

Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations: they often treat time series merely as text or images, failing to capture the patterns like trends and seasonalities needed to answer specific questions; and when trained on a mix of simple and complex tasks, simpler objectives often dominate the learning process, hindering the development of deep reasoning capabilities. To address these limitations, we propose the Pattern-Aware Alignment and Balanced Reasoning model (PATRA), introducing a pattern-aware mechanism that extracts trend and seasonality patterns from time series to achieve deep alignment. Furthermore, we design a task-aware balanced reward to harmonize learning across tasks of varying difficulty, incentivizing the generation of coherent Chains of Thought. Extensive experiments show that PATRA outperforms strong baselines across diverse Time Series Question Answering (TSQA) tasks, demonstrating superior cross-modal understanding and reasoning capability.

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。

AI总结：

摘要：

英文摘要：

相关论文