From Text to Time? Rethinking the Effectiveness of the Large Language Model for Time Series Forecasting
This work addresses the debate over LLM effectiveness in time series forecasting, providing empirical insights that are incremental to existing research.
The study investigated the effectiveness of using large language models (LLMs) as backbones for time series forecasting, finding that while LLMs show some promise, their forecasting performance is limited, with controlled experiments revealing this limitation in zero-shot and few-shot settings.
Using pre-trained large language models (LLMs) as the backbone for time series prediction has recently gained significant research interest. However, the effectiveness of LLM backbones in this domain remains a topic of debate. Based on thorough empirical analyses, we observe that training and testing LLM-based models on small datasets often leads to the Encoder and Decoder becoming overly adapted to the dataset, thereby obscuring the true predictive capabilities of the LLM backbone. To investigate the genuine potential of LLMs in time series prediction, we introduce three pre-training models with identical architectures but different pre-training strategies. Thereby, large-scale pre-training allows us to create unbiased Encoder and Decoder components tailored to the LLM backbone. Through controlled experiments, we evaluate the zero-shot and few-shot prediction performance of the LLM, offering insights into its capabilities. Extensive experiments reveal that although the LLM backbone demonstrates some promise, its forecasting performance is limited. Our source code is publicly available in the anonymous repository: https://anonymous.4open.science/r/LLM4TS-0B5C.