RETRIEVAL-AUGMENTED GENERATIVE AI FOR SMART LEARNING CONTENT
Kalit so'zlar
https://doi.org/10.65451/iqtisodiyotuzb.v5i7.13824Annotasiya
This article analyses the economic and pedagogical efficiency of retrieval-augmented generation (RAG) for the production of smart learning content. Drawing on industry analyses by MarketsandMarkets, Precedence Research, and NMSC, and on peer-reviewed studies from 2024–2026, it shows that the global RAG market is projected to grow from USD 1.94 billion in 2025 to USD 9.86 billion in 2030 (CAGR 38.4%), and that systems such as MEDRAG and Finetune-RAG improve answer accuracy by 18–21% and reduce hallucinations by 15–19% relative to baseline large language models.
Manbalar
1. Lewis P., Perez E., Piktus A. et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks // Advances in Neural Information Processing Systems. – 2020. – Vol. 33. – P. 9459–9474.
2. Gao Y., Xiong Y., Gao X. et al. Retrieval-Augmented Generation for Large Language Models: A Survey. Preprint, arXiv: 2312.10997, 2024.
3. Gupta S., Ranjan R., Singh S. N. A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions. Preprint, arXiv:2410.12837, 2024.
4. Zhao P., Zhang H., Yu Q. et al. Retrieval-Augmented Generation for AI-Generated Content: A Survey. Preprint, arXiv: 2402.19473, 2024.
5. Xiong G., Jin Q., Lu Z., Zhang A. Benchmarking Retrieval-Augmented Generation for Medicine (MIRAGE). Preprint, arXiv: 2402.13178, 2024.
6. Lee Z. P., Lin A., Tan C. Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation. Preprint, arXiv: 2505.10792, 2025.
7. Chitika. Retrieval-Augmented Generation (RAG): 2025 Definitive Guide [Electronic resource]. – 2025. – URL: https://www.chitika.com/retrieval-augmented-generation-rag-the-definitive-guide2025/
8. Mala C., et al. Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis. Preprint, arXiv: 2504.05324, 2025.
