面向基于大语言模型的时间序列异常检测的结构化频域证据
Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection
- Hanyang University（汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对现有基于LLM的时间序列异常检测方法缺乏显式频域证据的问题，提出证据增强的零样本TSAD框架，经多模型实验验证频域证据可提升检测性能。
AI中文摘要：
时间序列异常不仅可以表现为逐点偏差，还可以表现为重复时间结构的变化，如周期性偏移或局部振荡波动。然而，现有的基于大语言模型（LLM）的时间序列异常检测（TSAD）方法主要通过索引值、图表或去季节化表示来呈现时域证据，使频谱结构隐含。我们提出一种证据增强的零样本TSAD框架，该框架在保留索引去季节化观测值的同时，添加通过快速傅里叶变换（FFT）计算的紧凑频域证据。该证据在两种分辨率下构建：全局频域证据汇总序列级周期性上下文，局部频域证据捕获时间局部的频谱偏离。在使用InternVL2-LLaMA3-76B、Qwen2.5-VL-72B-Instruct、Gemini-2.5-Flash和GPT-4o的AnomLLM上进行实验，并在TSB-AD-U子集上进行评估，结果显示显式频域证据可改进基于LLM的TSAD基线。这些结果表明，频域证据可作为索引和去季节化时域输入的补充，用于零样本LLM-based TSAD。
英文摘要：
Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring temporal structure, such as shifted periodicity or localized oscillatory fluctuations. However, existing LLM-based time-series anomaly detection methods mainly expose time-domain evidence through indexed values, plots, or de-seasonalized representations, leaving spectral structure implicit. We propose an evidence-augmented zero-shot TSAD framework that preserves indexed de-seasonalized observations while adding compact frequency-domain evidence computed with the Fast Fourier Transform (FFT). The evidence is constructed at two resolutions: global frequency-domain evidence summarizes sequence-level periodic context, while local frequency-domain evidence captures time-localized spectral departures. Experiments on AnomLLM with InternVL2-LLaMA3-76B, Qwen2.5-VL-72B-Instruct, Gemini-2.5-Flash, and GPT-4o, together with evaluation on the TSB-AD-U subset, show that explicit frequency-domain evidence improves LLM-based TSAD baselines. These results suggest that frequency-domain evidence can complement indexed and de-seasonalized time-domain inputs for zero-shot LLM-based TSAD.
