错误反思提示：大语言模型能否成功理解错误？
Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?
AI总结：
本文提出错误反思提示（ERP）方法，在思维链基础上引入错误识别与纠错环节，使模型自行生成错误要点并集成到推理链中，从而提升推理稳健性与可解释性。
摘要：
针对语言模型的提示方法，如思维链（CoT），为问题求解呈现了直观的逐步过程。这些方法旨在使模型更好地理解处理给定任务的正确程序。尽管取得了这些进展，CoT 仍缺乏反思和纠错能力，可能导致模型持续犯下错误。因此，受人类执行此类任务能力的启发，我们提出错误反思提示（ERP），以进一步增强语言模型的推理能力。ERP 建立在 CoT 之上，是一种由错误答案、错误识别和正确答案组成的方法。这一过程使模型能够识别错误类型以及导致错误答案的步骤，从而使模型更好地辨别应避免哪些步骤、应采取哪些步骤。借助自动化 ERP 生成，模型能够自行生成错误要点，使错误识别和纠错得以集成到推理链中，并在该过程中产生可扩展性和可靠性。结果表明，ERP 可作为传统 CoT 的多功能补充，最终有助于实现更稳健、更强大的推理能力，并提高模型最终如何产生错误这一过程的可解释性。
英文摘要：
Prompting methods for language models, such as Chain-of-thought (CoT), present intuitive step-by-step processes for problem solving. These methodologies aim to equip models with a better understanding of the correct procedures for addressing a given task. Despite these advancements, CoT lacks the ability of reflection and error correction, potentially causing a model to perpetuate mistakes and errors. Therefore, inspired by the human ability for said tasks, we propose Error Reflection Prompting (ERP) to further enhance reasoning in language models. Building upon CoT, ERP is a method comprised of an incorrect answer, error recognition, and a correct answer. This process enables the model to recognize types of errors and the steps that lead to incorrect answers, allowing the model to better discern which steps to avoid and which to take. The model is able to generate the error outlines itself with automated ERP generation, allowing for error recognition and correction to be integrated into the reasoning chain and produce scalability and reliability in the process. The results demonstrate that ERP serves as a versatile supplement to conventional CoT, ultimately contributing to more robust and capable reasoning abilities along with increased interpretability in how models ultimately reach their errors.
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。
