From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle

2026-05-07

AI Summary

This study addresses the propensity of large language models to generate hallucinations and misleading information in educational settings by proposing a modular AI teaching assistant integrated with Moodle. Designed to foster a shift from surface-level learning to deep conceptual understanding, the system leverages retrieval-augmented generation (RAG) grounded exclusively in instructor-authorized course materials. It combines Socratic dialogue-based tutoring with a human-in-the-loop teacher oversight mechanism to ensure response fidelity. A novel dual-center architecture simultaneously supports student engagement in deep learning and enables real-time instructor monitoring of AI-generated content, thereby achieving high-fidelity, hallucination-free pedagogical interactions. Empirical evaluation demonstrates a faithfulness score of 0.97 on the Ragas benchmark and a user recommendation rating of 4.00 out of 5.00.

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.

Problem

• hallucination
• misinformation
• deep understanding
• AI tutoring
• education

Innovation

• Retrieval-Augmented Generation
• Socratic tutoring
• human-in-the-loop
• hallucination-free AI
• grounded LLM