The Correct Answer Trap: Pedagogically-Grounded Detection and Feedback for Hidden Misconceptions
Researchers demonstrate that automated educational feedback systems fail to detect hidden misconceptions when students arrive at correct answers through flawed reasoning, with fine-tuned classifiers achieving only 57% detection accuracy. A reasoning model reaches 84% accuracy but generates excessive false positives, prompting the proposal of a detect-verify-escalate pipeline that routes uncertain cases to diagnostic questions rather than immediate teacher escalation.