Mentor-KD: Making Small Language Models Better Multi-step Reasoners

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Hojae, Kim, Junho, Lee, SangKeun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914970194673664
author Lee, Hojae
Kim, Junho
Lee, SangKeun
author_facet Lee, Hojae
Kim, Junho
Lee, SangKeun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09037
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mentor-KD: Making Small Language Models Better Multi-step Reasoners
Lee, Hojae
Kim, Junho
Lee, SangKeun
Computation and Language
Artificial Intelligence
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.
title Mentor-KD: Making Small Language Models Better Multi-step Reasoners
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.09037