AI RESEARCH
Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation
arXiv CS.CL
•
ArXi:2604.17574v1 Announce Type: new Distractor generation (DG) remains a labor-intensive task that still significantly depends on domain experts. The task focuses on generating plausible yet incorrect options, known as distractors, for multiple-choice questions. A reliable distractor must be contextually relevant to the question and able to mislead examinees through implicit reasoning when identifying the correct answer.