Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation
This addresses the need for efficient and personalized AI tutors in education, though it is incremental as it builds on existing LLM and knowledge tracing methods.
The paper tackled the problem of distilling math word problem solving capabilities from large language models into smaller student models by using GPT-3 as a tutor to generate customized exercises based on the student's weaknesses, resulting in higher accuracy than LLMs like GPT-3 and PaLM across three benchmarks with fewer parameters.
In this paper, we present a novel approach for distilling math word problem solving capabilities from large language models (LLMs) into smaller, more efficient student models. Our approach is designed to consider the student model's weaknesses and foster a tailored learning experience by generating targeted exercises aligned with educational science principles, such as knowledge tracing and personalized learning. Concretely, we let GPT-3 be a math tutor and run two steps iteratively: 1) assessing the student model's current learning status on a GPT-generated exercise book, and 2) improving the student model by training it with tailored exercise samples generated by GPT-3. Experimental results reveal that our approach outperforms LLMs (e.g., GPT-3 and PaLM) in accuracy across three distinct benchmarks while employing significantly fewer parameters. Furthermore, we provide a comprehensive analysis of the various components within our methodology to substantiate their efficacy.