Time-series forecasting (TSF) finds broad applications in real-world
scenarios. Prompting off-the-shelf Large Language Models (LLMs) demonstrates
strong zero-shot TSF capabilities while preserving computational efficiency.
However, existing prompting methods oversimplify TSF as language next-token
predictions, overlooking its dynamic nature and lack of integration with
state-of-the-art prompt strategies such as Chain-of-Thought. Thus, we propose
LSTPrompt, a novel approach for prompting LLMs in zero-shot TSF tasks.
LSTPrompt decomposes TSF into short-term and long-term forecasting sub-tasks,
tailoring prompts to each. LSTPrompt guides LLMs to regularly reassess
forecasting mechanisms to enhance adaptability. Extensive evaluations
demonstrate consistently better performance of LSTPrompt than existing
prompting methods, and competitive results compared to foundation TSF models.

Time-series forecasting (TSF) finds broad applications in real-world scenarios, and this paper proposes LSTPrompt, a novel approach for prompting Large Language Models (LLMs) in zero-shot TSF tasks, which consistently outperforms existing prompting methods and achieves competitive results compared to foundation TSF models.