Position: What Can Large Language Models Tell Us about Time Series Analysis

Time series analysis is essential for comprehending the complexities inherentin various realworld systems and applications. Although large language models(LLMs) have recently made significant strides, the development of artificialgeneral intelligence (AGI) equipped with time series analysis capabilitiesremains in its nascent phase. Most existing time series models heavily rely ondomain knowledge and extensive model tuning, predominantly focusing onprediction tasks. In this paper, we argue that current LLMs have the potentialto revolutionize time series analysis, thereby promoting efficientdecision-making and advancing towards a more universal form of time seriesanalytical intelligence. Such advancement could unlock a wide range ofpossibilities, including time series modality switching and question answering.We encourage researchers and practitioners to recognize the potential of LLMsin advancing time series analysis and emphasize the need for trust in theserelated efforts. Furthermore, we detail the seamless integration of time seriesanalysis with existing LLM technologies and outline promising avenues forfuture research.