增强思维链提示中的迭代自举方法在大语言模型中的应用
Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models
AI总结：
本文提出Iter-CoT，一种迭代自举的思维链提示方法，通过自主纠错和选择中等难度示例，提升大语言模型在不同难度推理任务上的泛化性能，在十个数据集上取得竞争性结果。
摘要：
大语言模型（LLMs）通过将逐步的思维链（CoT）提示作为示例纳入，可以在各种推理任务上实现高效性能。然而，由LLMs生成的示例推理链容易出错，这随后可能导致推理过程中的错误推理。此外，不合适的示例（过于简单或复杂）会影响不同难度水平下的整体性能。我们引入了Iter-CoT（思维链提示中的迭代自举），一种用于选择示例和生成推理链的迭代自举方法。通过利用迭代自举，我们的方法使LLMs能够自主纠正错误，从而产生更精确和全面的推理链。同时，我们的方法选择具有中等难度水平的具有挑战性但可回答的问题及其推理链作为示例，这增强了LLMs在不同难度水平上的泛化能力。实验结果表明，Iter-CoT表现出优越性，在十个数据集上的三个不同推理任务中取得了有竞争力的性能。
英文摘要：
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by LLMs are prone to errors, which can subsequently lead to incorrect reasoning during inference. Furthermore, inappropriate exemplars (overly simplistic or complex), can affect overall performance among varying levels of difficulty. We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains. By utilizing iterative bootstrapping, our approach enables LLMs to autonomously rectify errors, resulting in more precise and comprehensive reasoning chains. Simultaneously, our approach selects challenging yet answerable questions accompanied by reasoning chains as exemplars with a moderate level of difficulty, which enhances the LLMs' generalizability across varying levels of difficulty. Experimental results indicate that Iter-CoT exhibits superiority, achieving competitive performance across three distinct reasoning tasks on ten datasets.
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。
