Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank

Autor:	Scarlatos, Alexander, Feng, Wanyong, Smith, Digory, Woodhead, Simon, Lan, Andrew
Rok vydání:	2024
Předmět:	Computer Science - Computers and Society Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Multiple-choice questions (MCQs) are commonly used across all levels of math education since they can be deployed and graded at a large scale. A critical component of MCQs is the distractors, i.e., incorrect answers crafted to reflect student errors or misconceptions. Automatically generating them in math MCQs, e.g., with large language models, has been challenging. In this work, we propose a novel method to enhance the quality of generated distractors through overgenerate-and-rank, training a ranking model to predict how likely distractors are to be selected by real students. Experimental results on a real-world dataset and human evaluation with math teachers show that our ranking model increases alignment with human-authored distractors, although human-authored ones are still preferred over generated ones. Comment: BEA workshop NAACL 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.05144 Zobrazit plný text záznamu View this record from Arxiv