Understanding the Role of Textual Prompts in LLM for Time Series Forecasting: an Adapter View
This work addresses the challenge of bridging the domain gap between texts and time series for researchers and practitioners in time series forecasting, offering incremental improvements through adapter-based methods.
The study tackled the problem of applying Large Language Models (LLMs) to time series forecasting by investigating how textual prompts improve prediction accuracy, finding that prompts act like adapters and that learnable parameters, not textual information, enhance accuracy, leading to the development of four adapters that further boost performance.
In the burgeoning domain of Large Language Models (LLMs), there is a growing interest in applying LLM to time series forecasting, with multiple studies focused on leveraging textual prompts to further enhance the predictive prowess. This study aims to understand how and why the integration of textual prompts into LLM can effectively improve the prediction accuracy of time series, which is not obvious at the glance, given the significant domain gap between texts and time series. Our extensive examination leads us to believe that (a) adding text prompts is roughly equivalent to introducing additional adapters, and (b) It is the introduction of learnable parameters rather than textual information that aligns the LLM with the time series forecasting task, ultimately enhancing prediction accuracy. Inspired by this discovery, we developed four adapters that explicitly address the gap between LLM and time series, and further improve the prediction accuracy. Overall,our work highlights how textual prompts enhance LLM accuracy in time series forecasting and suggests new avenues for continually improving LLM-based time series analysis.