Automatic Generation of Socratic Subquestions for Teaching Math Word Problems

TL;DR

This paper investigates how large language models can generate Socratic questions to improve math word problem solving and educational outcomes, combining question generation with problem-solving techniques.

Contribution

It introduces guided question generation schemes for LMs, demonstrating their effectiveness in enhancing problem-solving and educational value.

Findings

Generated questions improve math problem solver performance.

Question quality correlates with problem difficulty.

Preliminary user study shows educational potential.

Abstract

Socratic questioning is an educational method that allows students to discover answers to complex problems by asking them a series of thoughtful questions. Generation of didactically sound questions is challenging, requiring understanding of the reasoning process involved in the problem. We hypothesize that such questioning strategy can not only enhance the human performance, but also assist the math word problem (MWP) solvers. In this work, we explore the ability of large language models (LMs) in generating sequential questions for guiding math word problem-solving. We propose various guided question generation schemes based on input conditioning and reinforcement learning. On both automatic and human quality evaluations, we find that LMs constrained with desirable question properties generate superior questions and improve the overall performance of a math word problem solver. We conduct a preliminary user study to examine the potential value of such question generation models in the education domain. Results suggest that the difficulty level of problems plays an important role in determining whether questioning improves or hinders human performance. We discuss the future of using such questioning strategies in education.