From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle
Anna Ostrowska, Michał Kukla, Gabriela Majstrak, Jan Opala, Sebastian Pergała + 2 more
TLDR
A Moodle plugin uses RAG and LLMs for Socratic tutoring and educator content generation, ensuring high-quality, hallucination-free education.
Key contributions
- Developed an AI Teaching & Learning Assistant, a modular Moodle plugin.
- Uses Retrieval-Augmented Generation (RAG) to provide hallucination-free, high-quality education.
- Offers Socratic-based tutoring for students and a 'human-in-the-loop' content workspace for educators.
- Achieved high faithfulness (0.97) and user recommendation (4.00/5.00) in evaluations.
Why it matters
This paper introduces a practical AI tutoring system for Moodle that tackles LLM hallucination by grounding responses in teacher-provided materials. It offers a dual benefit, enhancing student learning through Socratic dialogue while empowering educators with supervised content creation tools.
Original Abstract
This demo paper describes the development of the AI Teaching \& Learning Assistant, a modular Moodle plugin that leverages Retrieval-Augmented Generation (RAG) to deliver high-quality, hallucination-free education. The system employs a dual-centric design, providing students with interactive, Socratic-based tutoring and educators with a "human-in-the-loop" workspace for supervised content generation. By grounding Large Language Model (LLM) responses in teacher-provided materials, the assistant addresses the risks of misinformation while encouraging deep conceptual mastery. Evaluation via the Ragas (LLM-as-a-Judge) framework and a preliminary user study confirms its effectiveness, achieving faithfulness scores up to 0.97 and a 4.00/5.00 recommendation rate.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.