Leveraging Graph Retrieval-Augmented Generation to Support Learners' Understanding of Knowledge Concepts in MOOCs

2025-05-15

AI Summary

Learners in MOOCs struggle with conceptual understanding; large language models (LLMs) suffer from hallucination; and existing retrieval-augmented generation (RAG) systems lack proactive pedagogical guidance. Method: We propose a graph-enhanced retrieval-and-generation framework integrating an educational knowledge graph (EduKG) and a personalized knowledge graph (PKG). It introduces two synergistic modules: PKG-driven personalized question generation and EduKG relation-aware conceptual question answering—enabling a paradigm shift from passive response to active learning guidance. The framework further incorporates graph neural network–based re-ranking, graph path reasoning, and RAG integration to improve retrieval precision and answer interpretability. Contribution/Results: Evaluated on three MOOCs via the CourseMapper platform with expert assessment, our approach achieves a 42% improvement in question relevance and a 38% gain in answer accuracy, demonstrating its effectiveness in supporting personalized conceptual understanding.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Massive Open Online Courses (MOOCs) lack direct interaction between learners and instructors, making it challenging for learners to understand new knowledge concepts. Recently, learners have increasingly used Large Language Models (LLMs) to support them in acquiring new knowledge. However, LLMs are prone to hallucinations which limits their reliability. Retrieval-Augmented Generation (RAG) addresses this issue by retrieving relevant documents before generating a response. However, the application of RAG across different MOOCs is limited by unstructured learning material. Furthermore, current RAG systems do not actively guide learners toward their learning needs. To address these challenges, we propose a Graph RAG pipeline that leverages Educational Knowledge Graphs (EduKGs) and Personal Knowledge Graphs (PKGs) to guide learners to understand knowledge concepts in the MOOC platform CourseMapper. Specifically, we implement (1) a PKG-based Question Generation method to recommend personalized questions for learners in context, and (2) an EduKG-based Question Answering method that leverages the relationships between knowledge concepts in the EduKG to answer learner selected questions. To evaluate both methods, we conducted a study with 3 expert instructors on 3 different MOOCs in the MOOC platform CourseMapper. The results of the evaluation show the potential of Graph RAG to empower learners to understand new knowledge concepts in a personalized learning experience.

Problem

• Addressing MOOC learners' difficulty in understanding concepts due to lack of instructor interaction
• Overcoming LLM hallucinations and unstructured materials in RAG for MOOCs
• Enhancing personalized learning by integrating EduKGs and PKGs in Graph RAG

Innovation

• Graph RAG pipeline with EduKGs and PKGs
• PKG-based Question Generation for personalization
• EduKG-based Question Answering using concept relationships