Boosting Large Language Models with Socratic Method for Conversational Mathematics Teaching
This work addresses the need for better conversational mathematics teaching tools for learners, though it appears incremental as it builds on existing LLM techniques with a specific teaching method.
The paper tackles the problem of enhancing mathematics teaching by large language models (LLMs) through a Socratic teaching-based approach, resulting in a model called SocraticLLM that shows great advantages over strong generative models in guiding learners via conversation.
With the introduction of large language models (LLMs), automatic math reasoning has seen tremendous success. However, current methods primarily focus on providing solutions or using techniques like Chain-of-Thought to enhance problem-solving accuracy. In this paper, we focus on improving the capability of mathematics teaching via a Socratic teaching-based LLM (\texttt{SocraticLLM}), which guides learners toward profound thinking with clarity and self-discovery via conversation. We collect and release a high-quality mathematical teaching dataset, named \texttt{SocraticMATH}, which provides Socratic-style conversations of problems with extra knowledge. Also, we propose a knowledge-enhanced LLM as a strong baseline to generate reliable responses with review, guidance/heuristic, rectification, and summarization. Experimental results show the great advantages of \texttt{SocraticLLM} by comparing it with several strong generative models. The codes and datasets are available on \url{https://github.com/ECNU-ICALK/SocraticMath}.