分隔符能否提升思维链提示的效果？
Can Separators Improve Chain-of-Thought Prompting?
AI总结：
针对思维链提示示例密集易引发大语言模型认知过载的问题，提出在每个示例末尾添加分隔符的COT-SEP方法，显著提升复杂推理任务表现，并测试了分隔符类型、位置在多模型上的效果。
摘要：
思维链（Chain-of-thought, CoT）提示是提升大语言模型（Large Language Models, LLMs）推理能力的一种简单有效的方法。CoT的基本思路是在输入提示中加入示例，让LLMs逐步拆解自身的思维过程。然而，CoT结构密集的提示示例可能会导致LLMs出现认知过载。受人类认知启发，我们提出COT-SEP方法，该方法在CoT提示的每个示例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自身的思维过程。有趣的是，实验结果表明，与不使用分隔符的普通CoT相比，COT-SEP显著提升了LLMs在复杂推理任务（如GSM8K、AQuA、CSQA）上的表现。我们还研究了分隔符的类型和位置的影响，在包括GPT-3.5-Turbo、GPT-4和LLaMA-2 7B等多个LLM上进行了测试。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
