Search papers, labs, and topics across Lattice.
This paper introduces a zero-shot time-series anomaly detection (TSAD) framework that integrates frequency-domain evidence alongside traditional time-domain inputs, utilizing the Fast Fourier Transform (FFT) to enhance detection capabilities. By preserving indexed de-seasonalized observations while adding both global and local frequency-domain evidence, the framework addresses the limitations of existing LLM-based methods that primarily focus on time-domain signals. Experiments demonstrate that this approach significantly improves the performance of various large language models (LLMs) on anomaly detection tasks, highlighting the importance of spectral structure in identifying anomalies.
Explicit frequency-domain evidence can dramatically enhance LLM-based time-series anomaly detection, revealing insights that time-domain methods miss.
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.
