Mentor-KD：使小型语言模型成为更好的多步推理器
Mentor-KD: Making Small Language Models Better Multi-step Reasoners
AI总结：
提出Mentor-KD框架，利用中间规模的导师模型增强CoT标注并提供软标签，有效解决LLM教师模型蒸馏集不足问题，将多步推理能力蒸馏至小型语言模型。
摘要：
大型语言模型（LLMs）通过利用思维链（CoT）提示，在各种复杂任务中展现了卓越的性能。近期，研究提出了一种知识蒸馏（KD）方法，即推理蒸馏，该方法通过微调语言模型来转移LLMs的推理能力，所用的多步推理依据由LLM教师生成。然而，在处理来自LLM教师模型的蒸馏集不足这一问题时，现有方法在以下两方面考虑欠妥：1）数据质量；2）软标签提供。本文提出Mentor-KD，在解决上述挑战的同时，有效地将LLMs的多步推理能力蒸馏到较小的LMs中。具体而言，我们利用一个导师模型——即中间规模且针对特定任务微调的模型——来增强额外的CoT标注，并在推理蒸馏过程中为学生模型提供软标签。我们进行了大量实验，证实了Mentor-KD在各种模型和复杂推理任务上的有效性。
英文摘要：
Large Language Models (LLMs) have displayed remarkable performances across various complex tasks by leveraging Chain-of-Thought (CoT) prompting. Recently, studies have proposed a Knowledge Distillation (KD) approach, reasoning distillation, which transfers such reasoning ability of LLMs through fine-tuning language models of multi-step rationales generated by LLM teachers. However, they have inadequately considered two challenges regarding insufficient distillation sets from the LLM teacher model, in terms of 1) data quality and 2) soft label provision. In this paper, we propose Mentor-KD, which effectively distills the multi-step reasoning capability of LLMs to smaller LMs while addressing the aforementioned challenges. Specifically, we exploit a mentor, intermediate-sized task-specific fine-tuned model, to augment additional CoT annotations and provide soft labels for the student model during reasoning distillation. We conduct extensive experiments and confirm Mentor-KD's effectiveness across various models and complex reasoning tasks.
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。
