Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization

ArXi:2510.19265v2 Announce Type: replace Difficulty-controllable question generation for reading comprehension has gained significant attention in the field of education as a fundamental tool for adaptive learning. Although several neural question generation methods have recently succeeded in controlling difficulty, conventional approaches still face two major limitations. First, they cannot directly generate multiple-choice questions, which are the most widely used question type in educational contexts.