APPLICATION OF RAG METHODOLOGY FOR EXPANDING THE CAPABILITIES OF LARGE LANGUAGE MODELS
Keywords:
LLM, RAG, LLAMAINDEX, TRULENS, EVALUATION OF EFFECTIVENESSAbstract
Large Language Models (LLMs) have become effective tools for understanding and generating text but have proven ineffective in addressing specialized tasks requiring specific information. The Retrieval-Augmented Generation (RAG) methodology proposes augmenting LLMs with specialized information to enhance their accuracy and reliability. This work examines the key components of RAG and explores their application to improve the efficiency of using large language models.
References
[1] T. Brown et al., "Language models are few-shot learners," in Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 1877–1901.
[2] H. Touvron et al., "Llama 2: Open foundation and fine-tuned chat models," arXiv preprint arXiv:2307.09288, 2023.
[3] Google, "Gemini: A family of highly capable multimodal models," 2023. [Online]. Available: https://goo.gle/GeminiPaper. [Accessed: Mar. 24, 2026].
[4] P. Lewis et al., "Retrieval-augmented generation for knowledge-intensive NLP tasks," in Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459–9474.
[5] Y. Gao et al., "Retrieval-augmented generation for large language models: A survey," arXiv preprint arXiv:2312.10997, 2023.
[6] TruLens, "The RAG Triad," 2024. [Online]. Available: https://www.trulens.org/trulens_eval/core_concepts_rag_triad/. [Accessed: Mar. 24, 2026].
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Наталія Полуектова
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
