ResearchBenchmarksQuestion Generation Evaluation on EduAgent (test)Follow74.17AccuracyChatEval64.633267.109169.58572.0609Mar 7, 2025Evaluation ResultsMethodMethodLinksAccuracyCAChatEval2025.0374.1756.67QG-SMS2025.0374.1763.33Vanilla2025.0370.8358.33Metrics2025.0369.1753.33Reference2025.0367.555CoT2025.036538.33Swap2025.036548.33