Saved in:
Bibliographic Details
Main Authors: Ostrowska, Anna, Kukla, Michał, Majstrak, Gabriela, Opala, Jan, Pergała, Sebastian, Skwarek, Jan, Wróblewska, Anna
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.06963
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915990986555392
author Ostrowska, Anna
Kukla, Michał
Majstrak, Gabriela
Opala, Jan
Pergała, Sebastian
Skwarek, Jan
Wróblewska, Anna
author_facet Ostrowska, Anna
Kukla, Michał
Majstrak, Gabriela
Opala, Jan
Pergała, Sebastian
Skwarek, Jan
Wróblewska, Anna
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06963
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle
Ostrowska, Anna
Kukla, Michał
Majstrak, Gabriela
Opala, Jan
Pergała, Sebastian
Skwarek, Jan
Wróblewska, Anna
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Information Retrieval
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.
title From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2605.06963