标题:【论文阅读-思维链的构造方法02】4.1.2Automatic Construction小节，论文合集

包含如下9篇论文：

  1. Large Language Models are Zero-Shot Reasoners

  1. Program of Thoughts Prompting:Disentangling Computation from Reasoning for Numerical Reasoning Tasks

  1. Plan-and-Solve Prompting:Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

  1. Automatic Chain of Thought Prompting in Large Language Models

  1. Reprompting:Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling

  1. Further Investigations into the Chain-of-Thought Prompting Paradigm

  1. A Study on the Impact of Chain-of-Thought Prompting on Large Language Models’Performance

  1. Enhancing Chain-of-Thought Reasoning in Large Language Models via Knowledge Integration

  1. Chain-of-Thought Prompting for Problem-Solving in Complex Tasks

这些论文探讨了大语言模型在零-shot推理中的应用，特别是思维链（Chain-of-Thought，CoT）构建方法的自动化。通过对多种方法的研究，作者们提出了不同的思维链提示技术，如计划-解决提示（Plan-and-Solve Prompting）和自动化思维链推理（Automatic Chain of Thought Prompting）。其中，Reprompting技术采用吉布斯采样方法，提升了思维链推理的准确性和效率。其他研究则关注如何通过集成知识来增强思维链的推理能力，以应对更为复杂的任务。