AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation
The integration of artificial intelligence (AI) in education has transformed content delivery and personalisation, with Retrieval-Augmented Generation (RAG) emerging as a promising architecture to enhance the accuracy and contextual relevance of AI-generated educational materials. This study aims to...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2025
|
| Online Access: | http://journalarticle.ukm.my/26732/1/58-68%20-.pdf http://journalarticle.ukm.my/26732/ http://ejournal.ukm.my/jpend |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1860590028288163840 |
|---|---|
| author | Norhayati Yahaya, Wan Ahmad Jailani Wan Ngah, A. Rahmad Ngah, Suhana Naziran Fadzilah Hamzah, Nor Faeza Salihin, Mohd Norazlinshah Mohd Salleh, Mahani Mokhtar, |
| author_facet | Norhayati Yahaya, Wan Ahmad Jailani Wan Ngah, A. Rahmad Ngah, Suhana Naziran Fadzilah Hamzah, Nor Faeza Salihin, Mohd Norazlinshah Mohd Salleh, Mahani Mokhtar, |
| author_sort | Norhayati Yahaya, |
| building | Tun Sri Lanang Library |
| collection | Institutional Repository |
| content_provider | Universiti Kebangsaan Malaysia |
| content_source | UKM Journal Article Repository |
| continent | Asia |
| country | Malaysia |
| description | The integration of artificial intelligence (AI) in education has transformed content delivery and personalisation, with Retrieval-Augmented Generation (RAG) emerging as a promising architecture to enhance the accuracy and contextual relevance of AI-generated educational materials. This study aims to systematically review the application, effectiveness, and challenges of RAG-powered educational content generation systems. The research employed a systematic literature review (SLR) design, guided by the PRISMA 2020 protocols. A total of 26 peer-reviewed articles published between 2020 and 2025 were selected from the Scopus database. No human participants were involved, as the study is based on literature. Data were extracted using a predefined matrix and analysed thematically to identify recurring patterns and contradictions. Findings revealed three major themes: (1) the dominance of retriever-generator pipelines and modular platforms such as OpenRAG and LearnRAG; (2) significant improvements in content factuality, student performance, and explainability; and (3) persistent limitations including infrastructure constraints, data bias, and ethical concerns. The review concludes that while RAG enhances educational AI systems, equitable access and responsible implementation remain critical. Implications include the need for policy frameworks, improved infrastructure, and future research on multilingual and domain-specific RAG applications. |
| format | Article |
| id | my-ukm.journal.26732 |
| institution | Universiti Kebangsaan Malaysia |
| language | en |
| publishDate | 2025 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| record_format | eprints |
| spelling | my-ukm.journal.267322026-03-17T04:50:50Z http://journalarticle.ukm.my/26732/ AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation Norhayati Yahaya, Wan Ahmad Jailani Wan Ngah, A. Rahmad Ngah, Suhana Naziran Fadzilah Hamzah, Nor Faeza Salihin, Mohd Norazlinshah Mohd Salleh, Mahani Mokhtar, The integration of artificial intelligence (AI) in education has transformed content delivery and personalisation, with Retrieval-Augmented Generation (RAG) emerging as a promising architecture to enhance the accuracy and contextual relevance of AI-generated educational materials. This study aims to systematically review the application, effectiveness, and challenges of RAG-powered educational content generation systems. The research employed a systematic literature review (SLR) design, guided by the PRISMA 2020 protocols. A total of 26 peer-reviewed articles published between 2020 and 2025 were selected from the Scopus database. No human participants were involved, as the study is based on literature. Data were extracted using a predefined matrix and analysed thematically to identify recurring patterns and contradictions. Findings revealed three major themes: (1) the dominance of retriever-generator pipelines and modular platforms such as OpenRAG and LearnRAG; (2) significant improvements in content factuality, student performance, and explainability; and (3) persistent limitations including infrastructure constraints, data bias, and ethical concerns. The review concludes that while RAG enhances educational AI systems, equitable access and responsible implementation remain critical. Implications include the need for policy frameworks, improved infrastructure, and future research on multilingual and domain-specific RAG applications. Penerbit Universiti Kebangsaan Malaysia 2025-11-30 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/26732/1/58-68%20-.pdf Norhayati Yahaya, and Wan Ahmad Jailani Wan Ngah, and A. Rahmad Ngah, and Suhana Naziran Fadzilah Hamzah, and Nor Faeza Salihin, and Mohd Norazlinshah Mohd Salleh, and Mahani Mokhtar, (2025) AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation. Jurnal Pendidikan Malaysia, 50 (2). pp. 58-68. ISSN 2600-8823 http://ejournal.ukm.my/jpend |
| spellingShingle | Norhayati Yahaya, Wan Ahmad Jailani Wan Ngah, A. Rahmad Ngah, Suhana Naziran Fadzilah Hamzah, Nor Faeza Salihin, Mohd Norazlinshah Mohd Salleh, Mahani Mokhtar, AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation |
| title | AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation |
| title_full | AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation |
| title_fullStr | AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation |
| title_full_unstemmed | AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation |
| title_short | AI-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation |
| title_sort | ai-powered learning content generation through retrieval-augmented generation for improved accuracy and personalisation |
| url | http://journalarticle.ukm.my/26732/1/58-68%20-.pdf http://journalarticle.ukm.my/26732/ http://ejournal.ukm.my/jpend |
| url_provider | http://journalarticle.ukm.my/ |