arXiv 2409.154612024-09-23cs.AIcs.CL

RAM2C：基于检索增强多角色多专家协作的文科教育聊天机器人

RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration

Center for Brain Inspired Computing Research (CBICR), Tsinghua University（清华大学脑启发计算研究中心）；Optical Memory National Engineering Research Center, Tsinghua University（清华大学光存储国家工程研究中心）；Tsinghua University-China Electronics Technology HIK Group Co. Joint Research Center for Brain-inspired Computing（清华大学-中国电子 hik 集团联合脑启发计算研究中心）；IDG/McGovern Institute for Brain Research, Tsinghua University（清华大学 IDG/麦戈文脑科学研究院）；Tsinghua University（清华大学）

Haoyu Huang, Tong Niu, Rui Yang, Luping Shi

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对大型语言模型在文科教育对话中难以兼顾人本化沟通、教学专长与安全伦理的问题，提出RAM2C框架，通过构建HTS引导知识库并组织多角色多专家协作生成对话数据集进行微调，有效提升了中文阅读教学的质量与安全性。

摘要：

近期，许多研究致力于将大型语言模型（LLMs）应用于教育对话。特别是在文科对话中，除了学科知识本身，教育者还必须兼顾人本化沟通（H）、教学专长（T）和安全伦理（S）（HTS）。然而，由于从现实世界收集大量符合HTS标准的教学对话作为训练语料成本高昂，现有LLMs在教学对话中的输出未达到人类标准。为解决此问题，我们设计了检索增强多角色多专家协作（RAM2C）框架，以自动生成此类对话数据。具体而言，我们首先建立了HTS引导的知识库，涵盖教学技能、心理学和安全伦理三个领域的知识。随后，RAM2C将经过上述不同知识库检索增强的LLMs组织成具有不同角色的多专家组，以生成符合HTS的教育对话数据集。接着，我们使用该数据集对LLMs进行微调。实证评估表明，RM2C赋能的LLMs在中文阅读教学中表现优异，能提供更具个性化且伦理安全的教学回复，证明了RAM2C的实用性与高质量。我们在 https://github.com/ram2c/ram2c 发布了实验。

英文摘要：

Recently, many studies focus on utilizing large language models (LLMs) into educational dialogues. Especially, within liberal arts dialogues, educators must balance \textbf{H}umanized communication, \textbf{T}eaching expertise, and \textbf{S}afety-ethics (\textbf{HTS}), besides the subject knowledge itself. However, due to collecting massive amounts of HTS-compliant teaching dialogues from real world as training corpus is expensive, the outputs of existing LLMs in teaching dialogues fall short of human standards. To address this, we design a Retrieval-augmented Multi-role Multi-expert Collaboration (RAM2C) framework to automatically generate such dialogues data. Specifically, we first establish HTS-guided knowledge bases, encompassing three domain knowledge in teaching skills, psychology, and safety ethics. Then, RAM2C organizes LLMs, which are retrieval-augmented by the above different knowledge bases, into multi-experts groups with distinct roles to generate the HTS-compliant educational dialogues dataset. We then fine-tuned the LLMs using this dataset. Empirical evaluations indicate that RM2C-empowered LLMs excel in Chinese reading teaching, offering more personalized, and ethically safe teaching response, demonstrating RAM2C's practicality and high quality. We release the experiments at \hyperlink{https://github.com/ram2c/ram2c}{https://github.com/ram2c/ram2c}.

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。