ERA-CoT：通过实体关系分析改进思维链
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
AI总结：
本文提出ERA-CoT方法，通过实体关系分析增强LLM对上下文的理解，并结合思维链提升多实体复杂场景下的推理与问答准确率，在GPT3.5上平均超越SOTA基线5.1%。
摘要：
大型语言模型（LLMs）在各种自然语言处理任务中取得了值得称赞的成就。然而，LLMs在处理涉及多个实体的复杂场景时仍然面临重大挑战。这些挑战源于需要多步推理的隐式关系。在本文中，我们提出了一种新颖的方法ERA-CoT，它通过捕获实体之间的关系来帮助LLMs理解上下文，并通过思维链（CoT）支持多样任务的推理。实验结果表明，ERA-CoT展示了我们提出的方法相较于当前CoT提示方法的优越性能，在GPT3.5上相比之前的SOTA基线平均显著提升了5.1%。我们的分析表明，ERA-CoT增强了LLM对实体关系的理解，显著提高了问答的准确性，并增强了LLMs的推理能力。
英文摘要：
Large language models (LLMs) have achieved commendable accomplishments in various natural language processing tasks. However, LLMs still encounter significant challenges when dealing with complex scenarios involving multiple entities. These challenges arise from the presence of implicit relationships that demand multi-step reasoning. In this paper, we propose a novel approach ERA-CoT, which aids LLMs in understanding context by capturing relationships between entities and supports the reasoning of diverse tasks through Chain-of-Thoughts (CoT). Experimental results show that ERA-CoT demonstrates the superior performance of our proposed method compared to current CoT prompting methods, achieving a significant improvement of an average of 5.1\% on GPT3.5 compared to previous SOTA baselines. Our analysis indicates that ERA-CoT increases the LLM's understanding of entity relationships, significantly improves the accuracy of question answering, and enhances the reasoning ability of LLMs.
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。
