为大模型时间序列异常检测添加频域证据，提升零样本检测效果
Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection
- 用快速傅里叶变换提取全局与局部频域特征作为补充证据
- 在AnomLLM等多模型上验证，频域证据显著提升异常检测性能
- 适合关注时序结构变化的工业监测与金融风控场景
时间序列异常不仅表现为点级偏离，还可能体现为周期性偏移或局部振荡波动等重复结构变化。现有基于大模型的时间序列异常检测方法主要依赖时域索引值、图表或去季节化表示暴露证据，频域结构隐含不显。本文提出一种增强型零样本时间序列异常检测框架，保留原始去季节化观测的同时，引入通过快速傅里叶变换（FFT）计算的紧凑频域证据。证据分为两级：全局频域证据总结序列级周期上下文，局部频域证据捕捉时间局部的谱异常。在AnomLLM与InternVL2-LLaMA3-76B、Qwen2.5-VL-72B-Instruct、Gemini-2.5-Flash、GPT-4o等模型上的实验，以及在TSB-AD-U子集的评估表明，显式频域证据能有效提升大模型基线表现。结果表明，频域证据可与索引值和去季节化时域输入互补，助力零样本大模型时间序列异常检测。
原文摘要 · Abstract (English)
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.
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。