Year: 2025
Type: conference-paper
Abstract: Anomaly detection in time series data is crucial across various domains. Traditional methods often struggle with continuously evolving time series requiring adjustment, whereas large language models (LLMs) and multi-modal LLMs (MLLMs) have emerged as promising zero-shot anomaly detectors by leveraging embedded knowledge. This study expands recent evaluations of MLLMs for zero-shot time series anomaly detection by exploring newer models, additional input representations, varying input sizes, and conducting further analyses. Our findings reveal that while MLLMs are effective for zero-shot detection, they still face limitations, such as effectively integrating both text and vision representations or handling longer input lengths. These challenges unveil diverse opportunities for future improvements.
Authors: Hao Niu, Guillaume Habault, Huy Quang Ung, Roberto Legaspi, Zhi Li, Yanan Wang, Donghuo Zeng, Julio Vizcarra, Masato Taya
Institution: KDDI Research (Japan)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W7084050469