从先前错误中检索的上下文原则
Retrieved In-Context Principles from Previous Mistakes
AI总结：
提出检索式上下文原则（RICP）框架，通过教师模型分析学生模型错误生成原则，聚类错误以增强覆盖，检索相关错误生成问题级原则，提升定制化，无需推理时干预，在七个推理基准上提升多种提示策略性能。
摘要：
上下文学习（ICL）在使用正确输入-输出示例将大型语言模型（LLMs）适应下游任务方面发挥了重要作用。最近的进展试图通过从错误中推导出的原则来改进模型性能，但这些方法缺乏定制化和错误覆盖不足。为了解决这些限制，我们提出了检索式上下文原则（RICP），一种新颖的教师-学生框架。在RICP中，教师模型分析学生模型的错误，生成避免类似错误的原因和见解。这些错误根据其根本原因进行聚类，以制定任务级原则，增强原则的错误覆盖。在推理过程中，为每个问题检索最相关的错误以创建问题级原则，提高所提供指导的定制化。RICP与现有提示方法正交，且在推理期间不需要教师模型的干预。在七个推理基准上的实验结果表明，RICP在应用于各种提示策略时有效提升了性能。
英文摘要：
In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output examples. Recent advances have attempted to improve model performance through principles derived from mistakes, yet these approaches suffer from lack of customization and inadequate error coverage. To address these limitations, we propose Retrieved In-Context Principles (RICP), a novel teacher-student framework. In RICP, the teacher model analyzes mistakes from the student model to generate reasons and insights for preventing similar mistakes. These mistakes are clustered based on their underlying reasons for developing task-level principles, enhancing the error coverage of principles. During inference, the most relevant mistakes for each question are retrieved to create question-level principles, improving the customization of the provided guidance. RICP is orthogonal to existing prompting methods and does not require intervention from the teacher model during inference. Experimental results across seven reasoning benchmarks reveal that RICP effectively enhances performance when applied to various prompting strategies.
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。
