用分层框架提升大模型对时序数据的理解能力
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
- 构建四层认知复杂度体系，统一时序推理任务定义
- 推出8.3万样本的层级化数据集HiTSR，支持思维链验证
- 融合视觉模式与精准表格，增强视觉语言模型时序感知
大语言模型对时序数据的全面理解仍面临重大挑战。现有研究受限于任务定义碎片化和基准存在内在模糊性，难以进行严谨评估及统一时序推理模型（TSRM）的开发。为此，我们通过一个四层递进认知复杂度的分类体系形式化定义时序推理（TSR）。引入HiTSR，一个包含8.3万样本的层级化时序推理数据集，涵盖多样任务组合并具备经验证的思维链（CoT）轨迹。基于HiTSR，我们提出LLaTiSA，一种强性能的TSRM，通过将可视化模式与精度校准的数值表格相结合，增强视觉-语言模型（VLMs）的时序感知能力。采用多阶段课程微调策略，LLaTiSA在多种时序推理任务及真实场景中均表现优异，展现出强大的分布外泛化能力。代码已开源。
原文摘要 · Abstract (English)
Comprehensive understanding of time series remains a significant challenge for Large Language Models (LLMs). Current research is hindered by fragmented task definitions and benchmarks with inherent ambiguities, precluding rigorous evaluation and the development of unified Time Series Reasoning Models(TSRMs). To bridge this gap, we formalize Time Series Reasoning (TSR) via a four-level taxonomy of increasing cognitive complexity. We introduce HiTSR, a hierarchical time series reasoning dataset comprising 83k samples with diverse task combinations and verified Chain-of-Thought (CoT) trajectories. Leveraging HiTSR, we propose LLaTiSA, a strong TSRM that integrates visualized patterns with precision-calibrated numerical tables to enhance the temporal perception of Vision-Language Models (VLMs). Through a multi-stage curriculum fine-tuning strategy, LLaTiSA achieves superior performance and exhibits robust out-of-distribution generalization across diverse TSR tasks and real-world scenarios. Our code is available at https://github.com/RainingNovember/LLaTiSA.
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。