Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models

TL;DR

This paper investigates the use of large language models to automate the creation of distractors for math multiple-choice questions, aiming to reduce manual effort but finding limitations in modeling student misconceptions.

Contribution

It explores various LLM-based methods for automated distractor generation in math MCQs and evaluates their effectiveness on real-world data.

Findings

LLMs can generate mathematically valid distractors

LLMs struggle to predict common student errors

Manual effort in creating high-quality distractors remains significant

Abstract

Multiple-choice questions (MCQs) are ubiquitous in almost all levels of education since they are easy to administer, grade, and are a reliable format in assessments and practices. One of the most important aspects of MCQs is the distractors, i.e., incorrect options that are designed to target common errors or misconceptions among real students. To date, the task of crafting high-quality distractors largely remains a labor and time-intensive process for teachers and learning content designers, which has limited scalability. In this work, we study the task of automated distractor generation in the domain of math MCQs and explore a wide variety of large language model (LLM)-based approaches, from in-context learning to fine-tuning. We conduct extensive experiments using a real-world math MCQ dataset and find that although LLMs can generate some mathematically valid distractors, they are less adept at anticipating common errors or misconceptions among real students.