Automated Distractor and Feedback Generation for Math Multiple-choice Questions via In-context Learning

TL;DR

This paper investigates using large language models to automate the creation of distractors and feedback messages for math multiple-choice questions, aiming to improve scalability and quality in educational assessments.

Contribution

It formulates the tasks of distractor and feedback generation, proposes an in-context learning approach, and introduces generative AI metrics for evaluation.

Findings

Significant room for improvement in automated distractor generation

Proposed in-context learning method shows promising results

Identified challenges and future directions for AI-assisted assessment

Abstract

Multiple-choice questions (MCQs) are ubiquitous in almost all levels of education since they are easy to administer, grade, and are a reliable form of assessment. An important aspect of MCQs is the distractors, i.e., incorrect options that are designed to target specific misconceptions or insufficient knowledge among students. To date, the task of crafting high-quality distractors has largely remained a labor-intensive process for teachers and learning content designers, which has limited scalability. In this work, we explore the task of automated distractor and corresponding feedback message generation in math MCQs using large language models. We establish a formulation of these two tasks and propose a simple, in-context learning-based solution. Moreover, we propose generative AI-based metrics for evaluating the quality of the feedback messages. We conduct extensive experiments on these tasks using a real-world MCQ dataset. Our findings suggest that there is a lot of room for improvement in automated distractor and feedback generation; based on these findings, we outline several directions for future work.