Aynur Aliyeva.
Application of Retrieval-Augmented Generation technology to teaching the subject of computer science
Retrieval-Augmented Generation (RAG) technology plays an important role in the field of artificial intelligence, combining the strengths of information retrieval systems with the generative capabilities of large language models. This study explores the application of RAG technology to further develop adaptive learning in computer science teaching. The application of RAG technology to computer science teaching will serve to overcome the limitations of traditional teaching methods through a question-based intelligent learning environment. The study was conducted on five computer science topics. A structured set of 20 questions with precise answers was developed for each topic. The structure based on these questions allows RAG technology to retrieve relevant information and generate specific explanations, which promotes deeper understanding and connections of computer science knowledge. The results show that RAG technology can significantly support learners in computer science teaching.
Keywords: Computer science, Adaptive learning, Retrieval-Augmented Generation Natural Language Processing (NLP), Large Language Models (LLM)
DOI: https://doi.org/10.54381/icp.2025.1.09
Application of Retrieval-Augmented Generation technology to teaching the subject of computer science
Retrieval-Augmented Generation (RAG) technology plays an important role in the field of artificial intelligence, combining the strengths of information retrieval systems with the generative capabilities of large language models. This study explores the application of RAG technology to further develop adaptive learning in computer science teaching. The application of RAG technology to computer science teaching will serve to overcome the limitations of traditional teaching methods through a question-based intelligent learning environment. The study was conducted on five computer science topics. A structured set of 20 questions with precise answers was developed for each topic. The structure based on these questions allows RAG technology to retrieve relevant information and generate specific explanations, which promotes deeper understanding and connections of computer science knowledge. The results show that RAG technology can significantly support learners in computer science teaching.
Keywords: Computer science, Adaptive learning, Retrieval-Augmented Generation Natural Language Processing (NLP), Large Language Models (LLM)
DOI: https://doi.org/10.54381/icp.2025.1.09