From Queries to Courses: SKYRAG’s Revolution in Learning Path Generation via Keyword-Based Document Retrieval
Large Language Models (LLMs) hold immense potential for transforming education by automating the generation of personalized learning paths. However, traditional LLMs often suffer from hallucinations and content irrelevance. To address these challenges, we propose SKYRAG, a Separated Keyword Retrieva...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10856105/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540514826584064 |
|---|---|
| author | Yosua Setyawan Soekamto Leonard Christopher Limanjaya Yoshua Kaleb Purwanto Dae-Ki Kang |
| author_facet | Yosua Setyawan Soekamto Leonard Christopher Limanjaya Yoshua Kaleb Purwanto Dae-Ki Kang |
| author_sort | Yosua Setyawan Soekamto |
| collection | DOAJ |
| description | Large Language Models (LLMs) hold immense potential for transforming education by automating the generation of personalized learning paths. However, traditional LLMs often suffer from hallucinations and content irrelevance. To address these challenges, we propose SKYRAG, a Separated Keyword Retrieval Augmentation Generation system that enhances the learning path generation process by integrating advanced retrieval mechanisms with LLMs. SKYRAG retrieves relevant course materials from Massive Open Online Course (MOOC) platforms, aligning them with individual learner profiles to provide personalized and coherent learning paths. Compared with Naïve RAG, SKYRAG demonstrates superior performance in terms of accuracy, relevance, and user satisfaction, as confirmed by human evaluations across four domains. By improving retrieval precision and addressing the limitations of traditional methods, SKYRAG represents a significant advancement in educational technology. This study contributes to the growing body of research on AI-driven learning systems and highlights SKYRAG’s potential for widespread adoption in dynamic educational environments. |
| format | Article |
| id | doaj-art-27b21a3b704b4955a6db4d8a19b19b80 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-27b21a3b704b4955a6db4d8a19b19b802025-02-05T00:01:13ZengIEEEIEEE Access2169-35362025-01-0113214342145510.1109/ACCESS.2025.353561810856105From Queries to Courses: SKYRAG’s Revolution in Learning Path Generation via Keyword-Based Document RetrievalYosua Setyawan Soekamto0https://orcid.org/0000-0001-5805-0359Leonard Christopher Limanjaya1https://orcid.org/0009-0003-5702-9955Yoshua Kaleb Purwanto2https://orcid.org/0009-0001-5973-0580Dae-Ki Kang3https://orcid.org/0000-0002-4147-2835Department of Computer Engineering, Dongseo University, Busan, South KoreaDepartment of Computer Engineering, Dongseo University, Busan, South KoreaDepartment of Computer Engineering, Dongseo University, Busan, South KoreaDepartment of Computer Engineering, Dongseo University, Busan, South KoreaLarge Language Models (LLMs) hold immense potential for transforming education by automating the generation of personalized learning paths. However, traditional LLMs often suffer from hallucinations and content irrelevance. To address these challenges, we propose SKYRAG, a Separated Keyword Retrieval Augmentation Generation system that enhances the learning path generation process by integrating advanced retrieval mechanisms with LLMs. SKYRAG retrieves relevant course materials from Massive Open Online Course (MOOC) platforms, aligning them with individual learner profiles to provide personalized and coherent learning paths. Compared with Naïve RAG, SKYRAG demonstrates superior performance in terms of accuracy, relevance, and user satisfaction, as confirmed by human evaluations across four domains. By improving retrieval precision and addressing the limitations of traditional methods, SKYRAG represents a significant advancement in educational technology. This study contributes to the growing body of research on AI-driven learning systems and highlights SKYRAG’s potential for widespread adoption in dynamic educational environments.https://ieeexplore.ieee.org/document/10856105/Retrieval augmented generationpersonalized learning pathlarge language modelseducational technologyhuman-centric design |
| spellingShingle | Yosua Setyawan Soekamto Leonard Christopher Limanjaya Yoshua Kaleb Purwanto Dae-Ki Kang From Queries to Courses: SKYRAG’s Revolution in Learning Path Generation via Keyword-Based Document Retrieval IEEE Access Retrieval augmented generation personalized learning path large language models educational technology human-centric design |
| title | From Queries to Courses: SKYRAG’s Revolution in Learning Path Generation via Keyword-Based Document Retrieval |
| title_full | From Queries to Courses: SKYRAG’s Revolution in Learning Path Generation via Keyword-Based Document Retrieval |
| title_fullStr | From Queries to Courses: SKYRAG’s Revolution in Learning Path Generation via Keyword-Based Document Retrieval |
| title_full_unstemmed | From Queries to Courses: SKYRAG’s Revolution in Learning Path Generation via Keyword-Based Document Retrieval |
| title_short | From Queries to Courses: SKYRAG’s Revolution in Learning Path Generation via Keyword-Based Document Retrieval |
| title_sort | from queries to courses skyrag x2019 s revolution in learning path generation via keyword based document retrieval |
| topic | Retrieval augmented generation personalized learning path large language models educational technology human-centric design |
| url | https://ieeexplore.ieee.org/document/10856105/ |
| work_keys_str_mv | AT yosuasetyawansoekamto fromqueriestocoursesskyragx2019srevolutioninlearningpathgenerationviakeywordbaseddocumentretrieval AT leonardchristopherlimanjaya fromqueriestocoursesskyragx2019srevolutioninlearningpathgenerationviakeywordbaseddocumentretrieval AT yoshuakalebpurwanto fromqueriestocoursesskyragx2019srevolutioninlearningpathgenerationviakeywordbaseddocumentretrieval AT daekikang fromqueriestocoursesskyragx2019srevolutioninlearningpathgenerationviakeywordbaseddocumentretrieval |