2023/08/07 by Hunter McNichols, McNichols, Hunter, Wanyong Feng +11 · 3 citations
Computer Science · Psychology · Social Sciences · #Computation and Language (cs.CL) #Educational Assessment and Pedagogy #Educational Technology and Assessment #FOS: Computer and information sciences #Innovative Teaching and Learning Methods
paper · pdf · doi:10.48550/arxiv.2308.03234
openalex publication_date 2023/08/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.