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

TL;DR

This paper introduces RAM2C, a retrieval-augmented multi-role multi-expert framework that automatically generates ethical, personalized educational dialogues for liberal arts teaching, improving LLM performance in Chinese reading instruction.

Contribution

The paper proposes a novel retrieval-augmented multi-role multi-expert collaboration framework for generating high-quality, HTS-compliant educational dialogue datasets to fine-tune LLMs.

Findings

RAM2C-generated datasets improve LLM responses in Chinese reading teaching.

LLMs fine-tuned with RAM2C data produce more personalized and ethically safe responses.

Empirical results demonstrate RAM2C's effectiveness in educational dialogue generation.

Abstract

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}.