Chain-of-thought (CoT) prompting is a simple and effective method for improving the reasoning capabilities of Large Language Models (LLMs). The basic idea of CoT is to let LLMs break down their thought processes step-by-step by putting exemplars in the input prompt. However, the densely structured prompt exemplars of CoT may cause the cognitive overload of LLMs. Inspired by human cognition, we introduce COT-SEP, a method that strategically employs separators at the end of each exemplar in CoT prompting. These separators are designed to help the LLMs understand their thought processes better while reasoning. Interestingly, it turns out that COT-SEP significantly improves the LLMs' performances on complex reasoning tasks (e.g., GSM8K, AQuA, CSQA), compared with the vanilla CoT, which does not use separators. We also study the effects of the type and the location of separators tested on multiple LLMs, including GPT-3.5-Turbo, GPT-4, and LLaMA-2 7B.

翻译：思维链（CoT）提示是一种简单而有效的方法，用于提升大语言模型（LLMs）的推理能力。CoT的基本思想是通过在输入提示中放置示例，让LLMs逐步分解其思维过程。然而，CoT中结构密集的提示示例可能导致LLMs的认知过载。受人类认知的启发，我们提出了COT-SEP方法，该方法在CoT提示中每个示例的末尾策略性地使用分隔符。这些分隔符旨在帮助LLMs在推理时更好地理解其思维过程。有趣的是，与未使用分隔符的原始CoT相比，COT-SEP显著提升了LLMs在复杂推理任务（例如GSM8K、AQuA、CSQA）上的表现。我们还研究了分隔符的类型和位置对多种LLMs（包括GPT-3.5-Turbo、GPT-4和LLaMA-2 7B）的影响。