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 eleven datasets.

通过使用迭代的引导选择，我们介绍了迭代链式思考（Iter-CoT）方法，该方法可以使大型语言模型（LLM）自主纠正错误，同时选择具有适度难度的挑战性问题作为样本，从而增强LLM对于不同难度的推理任务的泛化能力。实验结果表明Iter-CoT方法在11个数据集上展现出卓越的性能表现。 

在大型语言模型中通过迭代引导提高思维链路提示