paper
Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring
paperactiveprovisional
learning-to-prompt-improving-student-engagement-with-adaptive-llm-based-high-school-tutoring-416e6eab·1 events·first seen 2d agoAliases: Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring
More like this (12)
Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedbackstudent-teacher promptingPersonalized Evaluation as LearningTraining LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference OptimizationRevising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussionsactive learningEDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM GradingMultimodal Continual Instruction TuningHuman Adults and LLMs as Scientists: Who Benefits from Active Exploration?When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context LearningSecurity and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs RespondLLM Pretraining
Recent events (1)
Adaptive LLM tutoring system with subject-aware prompt routing improves high-school student engagement
Researchers develop and evaluate an LLM-based tutoring system that uses a learned prompt routing model to dynamically select pedagogical strategies based on 14 features extracted from conversation transcripts. The system was trained in simulation and deployed in an A/B test with 359 high-school students (656 conversations), showing sim-to-real transfer and reducing required interactions by ~3 turns. A stochastic routing strategy achieved a notably higher exercise conversion rate (28.1%) compared to a greedy router (19.1%) and static baseline (19.6%).