Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mohamed Abdelmagied, Mohamed Amine Chatti, Shoeb Joarder, Qurat Ul Ain, Rawaa Alatrash

TL;DR

MOOC learners often struggle with concept comprehension due to limited instructor interaction and the risk of hallucinations from standalone LLMs. The paper introduces a Graph Retrieval-Augmented Generation pipeline that leverages Educational Knowledge Graphs (EduKGs) and Personal Knowledge Graphs (PKGs) within the CourseMapper MOOC platform, featuring PKG-based Question Generation to tailor prompts and EduKG-based Question Answering to provide evidence-backed answers. It automatically constructs EduKGs and PKGs, demonstrates the workflow with a user scenario, and evaluates both components through expert-instructor studies across three MOOCs, highlighting strong linguistic relevance for QG but challenges in QA accuracy. The approach offers a structured, personalized, and evidence-grounded learning experience that scales learner guidance in MOOCs, while pointing to avenues for richer data sources and enhanced reasoning to improve reliability.

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.

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

TL;DR

MOOC learners often struggle with concept comprehension due to limited instructor interaction and the risk of hallucinations from standalone LLMs. The paper introduces a Graph Retrieval-Augmented Generation pipeline that leverages Educational Knowledge Graphs (EduKGs) and Personal Knowledge Graphs (PKGs) within the CourseMapper MOOC platform, featuring PKG-based Question Generation to tailor prompts and EduKG-based Question Answering to provide evidence-backed answers. It automatically constructs EduKGs and PKGs, demonstrates the workflow with a user scenario, and evaluates both components through expert-instructor studies across three MOOCs, highlighting strong linguistic relevance for QG but challenges in QA accuracy. The approach offers a structured, personalized, and evidence-grounded learning experience that scales learner guidance in MOOCs, while pointing to avenues for richer data sources and enhanced reasoning to improve reliability.

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.
Paper Structure (11 sections, 3 figures, 2 tables)

This paper contains 11 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. EduKG and PKG Construction in CourseMapper
  3. Methodology
  4. User Scenario
  5. PKG-based Question Generation
  6. EduKG-based Question Answering
  7. Evaluation
  8. PKG-based Question Generation Evaluation
  9. EduKG-based Question Answering Evaluation
  10. Conclusion and Future Work
  11. Disclosure of Interests.

Figures (3)

  • Figure 1: An overview of an example EduKG in CourseMapper: Each Learning Material (LM) contains Slides (S), Each Slide consists of Main Concepts (MCs) which also correspond to Wikipedia Articles. Each MC is related to Related Concepts (RCs) which are further concepts extracted from the MC article on Wikipedia.
  • Figure 2: A user scenario of the PKG-based Question Generation and EduKG-based Question Answering in CourseMapper
  • Figure 3: An overview of the pipeline for implementing PKG-based Question Generation and EduKG-based Question Answering with the steps: (A) graph-guided retrieval for Question Generation, (P1) Question Generation prompt template, (B) graph-based re-ranking, (C) graph-based indexing, (D) and (E) graph-guided retrieval for Question Answering, (P2) Extractive Question Answering prompt template, (P3) EduKG retrieval prompt template, (F) Answers with citations, (G) Highlighted answers