Context information can be more important than reasoning for time series forecasting with a large language model
This addresses the problem of optimizing LLM prompts for time series forecasting, which is incremental as it builds on existing prompting techniques.
The paper investigates the use of large language models (LLMs) for time series forecasting and finds that providing proper context information, without specific reasoning prompts, achieves performance comparable to the best-performing prompts, indicating context can be more crucial than reasoning in this task.
With the evolution of large language models (LLMs), there is growing interest in leveraging LLMs for time series tasks. In this paper, we explore the characteristics of LLMs for time series forecasting by considering various existing and proposed prompting techniques. Forecasting for both short and long time series was evaluated. Our findings indicate that no single prompting method is universally applicable. It was also observed that simply providing proper context information related to the time series, without additional reasoning prompts, can achieve performance comparable to the best-performing prompt for each case. From this observation, it is expected that providing proper context information can be more crucial than a prompt for specific reasoning in time series forecasting. Several weaknesses in prompting for time series forecasting were also identified. First, LLMs often fail to follow the procedures described by the prompt. Second, when reasoning steps involve simple algebraic calculations with several operands, LLMs often fail to calculate accurately. Third, LLMs sometimes misunderstand the semantics of prompts, resulting in incomplete responses.