让大模型学会自我纠错，提升推理可靠性。
Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?
- 在思维链基础上增加错误识别与修正步骤
- 模型能自动生成错误分析并修正答案
- 适合需要高可靠推理的场景如教育、医疗
提示方法如思维链（CoT）通过逐步推理提升语言模型的问题解决能力，但缺乏反思与错误修正机制，可能导致错误持续传递。为此，我们提出错误反思提示（ERP），在CoT基础上引入错误答案、错误识别和正确答案三阶段。该方法使模型能够自主识别错误类型及导致错误的步骤，从而明确应避免或采纳的操作。通过自动化生成ERP，实现错误识别与修正融入推理链，提升了过程的可扩展性与可靠性。实验表明，ERP作为传统CoT的补充，显著增强模型推理的鲁棒性与可解释性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。