通过关系元组、验证和动态反馈提升大型语言模型的算术推理能力
Improving Arithmetic Reasoning Ability of Large Language Models through Relation Tuples, Verification and Dynamic Feedback
AI总结：
本文提出利用半结构化关系元组表示大型语言模型推理步骤，结合本地代码解释器自动验证与动态反馈机制，有效提升了模型在算术数据集上的推理能力。
摘要：
当前大型语言模型推理步骤中使用的表示形式主要可分为两大类：（1）自然语言，难以验证；（2）非自然语言，通常是编程代码，对于不熟悉编程的人来说难以阅读。在本文中，我们提出使用一种半结构化形式来表示大型语言模型的推理步骤。具体而言，我们使用关系元组，它不仅人类可读，而且机器友好，并且比自然语言更容易验证。我们实现了一个包含三个主要组件的框架：（1）将关系元组引入大型语言模型的推理步骤中；（2）基于关系元组，通过本地代码解释器实现推理步骤的自动验证过程；（3）集成一种简单有效的动态反馈机制，我们发现该机制有助于大型语言模型的自我改进。在各种算术数据集上的实验结果证明了我们的方法在提升大型语言模型算术推理能力方面的有效性。源代码可在 https://github.com/gpgg/art 获取。
英文摘要：
Current representations used in reasoning steps of large language models can mostly be categorized into two main types: (1) natural language, which is difficult to verify; and (2) non-natural language, usually programming code, which is difficult for people who are unfamiliar with coding to read. In this paper, we propose to use a semi-structured form to represent reasoning steps of large language models. Specifically, we use relation tuples, which are not only human-readable but also machine-friendly and easier to verify than natural language. We implement a framework that includes three main components: (1) introducing relation tuples into the reasoning steps of large language models; (2) implementing an automatic verification process of reasoning steps with a local code interpreter based on relation tuples; and (3) integrating a simple and effective dynamic feedback mechanism, which we found helpful for self-improvement of large language models. The experimental results on various arithmetic datasets demonstrate the effectiveness of our method in improving the arithmetic reasoning ability of large language models. The source code is available at https://github.com/gpgg/art.
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。
