Efficient Usage of RAG Systems in the World of LLMs

Full Text

Abstract

The integration of Retrieval-Augmented Generation (RAG) systems with Large Language Models (LLMs) has revolutionized the field of Natural Language Processing (NLP). By leveraging RAG techniques, LLMs can access a broader range of information, improve coherence, and enhance the relevance of generated text. This paper explores the efficient usage of RAG systems in LLMs, highlighting their benefits, applications, and future implications.

Figures

Figure 1: RAG-based application architecture.

References

Patrick Lewis, Ethan Perez, Aleksandra Piktus, et al. (2020) Retrieval-augmented generation for knowledge-intensive NLP tasks. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS '20). Curran Associates Inc., Red Hook, NY, USA, Article 793, 9459-9474.
M Wang, M Wang, X Xu, et al. (2024) Unleashing ChatGPT's Power: A Case Study on Optimizing Information Retrieval in Flipped Classrooms via Prompt Engineering. IEEE Transactions on Learning Technologies. 17: 629-641.
D Park, G-t An, C Kamyod et al. (2023) A Study on Performance Improvement of Prompt Engineering for Generative AI with a Large Language Model. Journal of Web Engineering. 22: 1187-1206.
Jurafsky Daniel, H James Martin. (2000) Speech and language processing : An introduction to natural language processing, computational linguistics, and speech recognition. Upper Saddle River, N.J.: Prentice Hall.
Galke L, Saleh A, Scherp A. (2017) Word embeddings for practical information retrieval. In: M Eibl, M Gaedke (Eds.). INFORMATIK. 2155-2167.
Niklas Muennighoff, Nouamane Tazi, Loic Magne, et al. (2023) MTEB: Massive Text Embedding Benchmark. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2014–2037, Dubrovnik, Croatia. Association for Computational Linguistics.
https://huggingface.co/spaces/mteb/leaderboard
Vaswani A, Shazeer N, Parmar N, et al. (2017) Attention is all you need. Advances in Neural Information Processing Systems. 5999-6009.
Radford A, Narasimhan K. (2018) Improving language understanding by generative pre-training.
Devlin J, Chang MW, Lee K, et al. (2019) BERT: Pretraining of deep bidirectional transformers for language understanding. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, 1(Mlm), 4171-4186.
K Jarvelin J Kekalainen. (2002) Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS). 20(4):422-446.
Levy M, Jacoby A, Goldberg Y. (2024) Same task, more tokens: The impact of input length on the reasoning performance of large language models. ArXiv, abs/2402.14848.

Cite This Article

Priyank Jayantilal Rathod, Anurag. Efficient Usage of RAG Systems in the World of LLMs. January 20, 2026; 3(1): 138-141. OSP ID: OSP-135; Available at: https://www.openscopepublications.com/articles/pdf/OSP-135.pdf

Retrieval-Augmented Generation (RAG) Embeddings Large Language Models Natural Language Processing.

[bib1] Patrick Lewis, Ethan Perez, Aleksandra Piktus, et al. (2020) Retrieval-augmented generation for knowledge-intensive NLP tasks. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS '20). Curran Associates Inc., Red Hook, NY, USA, Article 793, 9459-9474.

[bib2] M Wang, M Wang, X Xu, et al. (2024) Unleashing ChatGPT's Power: A Case Study on Optimizing Information Retrieval in Flipped Classrooms via Prompt Engineering. IEEE Transactions on Learning Technologies. 17: 629-641.

[bib3] D Park, G-t An, C Kamyod et al. (2023) A Study on Performance Improvement of Prompt Engineering for Generative AI with a Large Language Model. Journal of Web Engineering. 22: 1187-1206.

[bib4] Jurafsky Daniel, H James Martin. (2000) Speech and language processing : An introduction to natural language processing, computational linguistics, and speech recognition. Upper Saddle River, N.J.: Prentice Hall.

[bib5] Galke L, Saleh A, Scherp A. (2017) Word embeddings for practical information retrieval. In: M Eibl, M Gaedke (Eds.). INFORMATIK. 2155-2167.

[bib6] Niklas Muennighoff, Nouamane Tazi, Loic Magne, et al. (2023) MTEB: Massive Text Embedding Benchmark. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2014–2037, Dubrovnik, Croatia. Association for Computational Linguistics.

[bib7] https://huggingface.co/spaces/mteb/leaderboard

[bib8] Vaswani A, Shazeer N, Parmar N, et al. (2017) Attention is all you need. Advances in Neural Information Processing Systems. 5999-6009.

[bib9] Radford A, Narasimhan K. (2018) Improving language understanding by generative pre-training.

[bib10] Devlin J, Chang MW, Lee K, et al. (2019) BERT: Pretraining of deep bidirectional transformers for language understanding. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, 1(Mlm), 4171-4186.

[bib11] K Jarvelin J Kekalainen. (2002) Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS). 20(4):422-446.

[bib12] Levy M, Jacoby A, Goldberg Y. (2024) Same task, more tokens: The impact of input length on the reasoning performance of large language models. ArXiv, abs/2402.14848.