给对的时间序列信息比复杂推理更能提升大模型预测效果
Context information can be more important than reasoning for time series forecasting with a large language model
- 仅提供合适上下文信息，无需复杂推理提示即可达最佳性能
- 长短期时间序列预测中，上下文信息表现优于特定推理提示
- 适合关注上下文设计而非复杂推理的时序预测研究者
随着大语言模型（LLMs）的发展，利用其进行时间序列任务的兴趣日益增长。本文通过考察现有及新提出的提示技术，探索了LLM在时间序列预测中的特性。评估了短时序与长时序的预测表现。结果表明，没有一种提示方法适用于所有场景。观察发现，仅提供与时间序列相关的适当上下文信息，不附加额外推理提示，即可达到各情况下最优提示的性能水平。由此推断，在时间序列预测中，提供恰当的上下文信息可能比特定推理提示更为关键。此外还识别出若干提示策略的弱点：第一，LLM常无法遵循提示中描述的步骤；第二，当推理步骤涉及多个操作数的简单代数计算时，LLM常出现计算错误；第三，LLM有时会误解提示语义，导致响应不完整。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。