Tahmid Al Hannan, Diego Garcia, Alex Njoroge, Suha Al Juboori, Tarek Sakakini (2026) — arXiv preprint.
Addresses the lag between LLM integration into K-12/higher education and reliable methods for evaluating pedagogical quality. The authors introduce a knowledge-distillation approach to automate AI-tutor evaluation, distilling expert judgments of pedagogical quality into a scalable evaluator.
Directly advances intelligent-tutoring evaluation and automated-grading of tutor behavior across k-12 and higher-ed, building on llm-based assessment. It complements ai-tutor-behavioral-evaluation and the ai-tutor-effectiveness-review, offering a practical route to scalable, expert-aligned tutor quality measurement.
Related Pages
- intelligent-tutoring — AI tutor evaluation
- automated-grading — Scalable tutor grading
- llm — LLM-based assessment
- k-12 — K-12 tutor deployment
- higher-ed — Higher-ed deployment
- ai-tutor-behavioral-evaluation — Behavioral evaluation axis