Automated Distractor and Feedback Generation for Math Multiple-choice Questions via In-context Learning
This addresses scalability issues for teachers and content designers in education, but it is incremental as it builds on existing in-context learning methods.
The paper tackled the problem of automating the generation of distractors and feedback for math multiple-choice questions, which is labor-intensive for educators, by using large language models with in-context learning, but found significant room for improvement in performance.
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.