Retrieval-Augmented Generation for Question Answering and Beyond: A State-of-the-Art Review
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V7I2P104Keywords:
Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Question Answering (QA), Natural Language Processing (NLP), Generative Models, Open-Domain Question AnsweringAbstract
Large language models (LLMs) are improved by RAG, a disruptive paradigm in natural language processing that combines generation with external knowledge retrieval. Unlike conventional models that rely solely on a parametric internal memory component, the RAG model can retrieve the required information, whether structured or unstructured and merge it into the answer-generation process, aiding factual grounding, enriched context and greater logical capacity. The primary RAG concepts have been systematically summarized in this paper, including system architecture, retrieval strategies, embedding techniques, reranking strategies and knowledge-aware generation frameworks. Its use in open-domain question answering applications has demonstrated that RAG can be used to aid evidence-based reasoning, multi-hop query answering, and interpretability. Outside QA, RAG has been useful in dialogue systems, domain-specific assistants, scientific summarization, enterprise knowledge systems, medical reasoning systems and code generators, demonstrating the applicability of RAG to practical environments. The recent developments have encompassed hybrid retrieval mechanisms, graph-based augmentation, multimodal integration and agent-like reasoning that further add on to the capabilities of RAG. This review outlines that, with summarization of theoretical backgrounds, practical applications and developments RAG is increasingly taking up prominence as a dependable framework for knowledge-based intelligent systems that are able to be scaled. The discussion contributes to understanding the evolution of RAG and demonstrates how retrieval-compatible generation can further enhance the effectiveness of current LLM-based applications.
References
[1] Sita Rama Praveen Madugula and Nihar Malali, “AI-powered life insurance claims adjudication using LLMs and RAG Architectures,” Int. J. Sci. Res. Arch., vol. 15, no. 1, April, pp. 460–470, Apr. 2025, doi: 10.30574/ijsra.2025.15.1.0867.
[2] P. Lewis et al., “Retrieval-augmented generation for knowledge-intensive NLP tasks,” Adv. Neural Inf. Process. Syst., vol. 33, pp. 9459–9474, 2020.
[3] F. J. C. Faust et al., “Embedding-based retrieval techniques for feeds,” 11960550, 2024
[4] A. Nerella and J. W. Sajja, “Responsible AI in Enterprise Applications: Balancing Innovation and Compliance,” in Computer Fraud and Security, MA Healthcare Ltd, Oct. 2023, p. 10. doi: 10.52710/cfs. 744.
[5] S. Gupta, R. Ranjan, and S. N. Singh, “A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions,” vol. 1, 2024, doi: http://dx.doi.org/10.48550/arXiv.2410.12837.
[6] Y. Mao et al., “Generation-augmented retrieval for open-domain question answering,” arXiv Prepr. arXiv2009.08553, 2020.
[7] N. K. R. Choppa and N. Kolli, “Contextual Frameworks for Agentic AI: Engineering Adaptive Memory and Retrieval Mechanisms,” Comput. Fraud Secur., vol. 2024, no. 11, pp. 395–406, 2024, doi: https://doi.org/10.52710/cfs.747.
[8] W. Meng, Y. Li, L. Chen, and Z. Dong, “Using the Retrieval-Augmented Generation to Improve the Question-Answering System in Human Health Risk Assessment: The Development and Application,” Electronics, vol. 14, no. 2, 2025, doi: 10.3390/electronics14020386.
[9] Siddhesh Amrale, “A Novel Generative AI-Based Approach for Robust Anomaly Identification in High-Dimensional Datasets,” Int. J. Adv. Res. Sci. Commun. Technol., pp. 709–721, Oct. 2024, doi: 10.48175/IJARSCT-19900D.
[10] J. Huang et al., “Layered Query Retrieval: An Adaptive Framework for Retrieval-Augmented Generation in Complex Question Answering for Large Language Models,” Appl. Sci., vol. 14, no. 23, p. 11014, Nov. 2024, doi: 10.3390/app142311014.
[11] J. Genesis, “Retrieval-Augmented Text Generation: Methods, Challenges, and Applications,” Apr. 2025. doi: 10.20944/preprints202504.0443.v1.
[12] J. Huang and K. C. Chang, “Towards Reasoning in Large Language Models: A Survey,” 2022.
[13] J. Saad-falcon, C. Potts, and O. Khattab, “ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems,” 2021.
[14] J. Zhang, Graph-ToolFormer : To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT, vol. 1, no. 1. Association for Computing Machinery, 2023.
[15] U. Dodda, H. Volikatla, and J. R. Vummadi, “Exploring the Role of AI-Enhanced Chatbots in Automating Recruitment Processes in Human Capital Management Systems,” Int. J. Emerg. Trends Comput. Sci. Inf. Technol., vol. 6, no. 3, July, pp. 28–36, 2025, doi: https://doi.org/10.63282/3050-9246.IJETCSIT-V6I3P104.
[16] S. B. Karri, S. Gawali, S. Rayankula, and P. Vankadara, “AI Chatbots in Banking: Transforming Customer Service and Operational Efficiency,” 2025. doi: 10.3233/FAIA251498.
[17] Y. Gao et al., “Retrieval-Augmented Generation for Large Language Models : A Survey,” pp. 1–21, 2024.
[18] R. Karne, P. K. Pativada, and A. Dudhipala, “DFIR-chain-integrating memory forensics, YARA scanning, and LLM summarization for automated triage,” in 2025 9th International Conference on Inventive Systems and Control (ICISC), Coimbatore, India: IEEE, 2025, pp. 1263–1268, October. doi: 10.1109/ICISC65841.2025.11187513.
[19] P. R. Marapatla, “NEXT-GEN ENTERPRISE BI: A STRATEGIC GUIDE TO AI-INFUSED REPORTING SOLUTIONS,” TPM – Testing, Psychom. Methodol. Appl. Psychol., vol. 32, 2025.
[20] D. C. Youvan, “Retrieval-Augmented Generation (RAG): Advancing AI with Dynamic Knowledge Integration,” no. January, 2025, doi: 10.13140/RG.2.2.30888.89606.
[21] S. S. Saisuman Singamsetty, “Hy-Search: A Hybrid Retrieval-Augmented Framework for Factual and Context-Aware Enterprise Knowledge Discovery,” in Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025), Springer Nature, 2025, pp. 431, Dec. doi: https://doi.org/10.2991/978-94-6463-978-0_37.
[22] A. Bhad, “Optimizing Latency and Relevance in RAG Pipelines: Leveraging ScaNN for Scalable Semantic Search in LLM Applications,” 2025.
[23] Y. Macha and S. K. Pulichikkunnu, “A Survey of DevOps Practices for Machine Learning and Artificial Intelligence Workflows in Modern Software Development,” ESP J. Eng. Technol. Adv., vol. 4, no. 3, pp. 200–208, 2024, doi: 10.56472/25832646/JETA-V4I3P121.
[24] D. Patel, “AI-Enhanced Natural Language Processing for Improving Web Page Classification Accuracy,” ESP J. Eng. Technol. Adv., vol. 4, no. 1, pp. 133–140, 2024, doi: 10.56472/25832646/JETA-V4I1P119.
[25] S. Garg, “Predictive Analytics and Auto Remediation using Artificial Intelligence and Machine Learning in Cloud Computing Operations,” Int. J. Innov. Res. Eng. Multidiscip. Phys. Sci., vol. 7, no. 2, March-April, pp. 01–05, 2019, doi: http://dx.doi.org/10.5281/zenodo.15362327.
[26] F. Mai, N. Pappas, I. Montero, N. Smith, and J. Henderson, “Plug and Play Autoencoders for Conditional Text Generation,” 2020, pp. 6076–6092. doi: 10.18653/v1/2020.emnlp-main.491.
[27] N. Zamzami and N. Bouguila, “A novel minorization–maximization framework for simultaneous feature selection and clustering of high-dimensional count data,” Pattern Anal. Appl., 2023, doi: 10.1007/s10044-022-01094-z.
[28] J. Genesis and F. Keane, “Integrating Knowledge Retrieval with Generation: A Comprehensive Survey of RAG Models in NLP,” Preprints, Apr. 2025, doi: 10.20944/preprints202504.0351.v1.
[29] Z. Xu et al., Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering, vol. 1, no. 1. Association for Computing Machinery, 2024. doi: 10.1145/3626772.3661370.
[30] D. Bhattacharjee, “Design and Evaluation of Deep Generative AI Model for Intrusion Detection in Cyber Threat Monitoring,” in 2025 7th International Symposium on Advanced Electrical and Communication Technologies (ISAECT), Mohali, Punjab, India: IEEE, 2025, pp. 1–6, December. doi: https://doi.org/10.1109/ISAECT68904.2025.11318752.
[31] C. Tayal, “Data Quality Assessment and Cleaning Framework for Healthcare Databases Using Python,” Int. J. Artif. Intell. Data Sci. Mach. Learn., vol. 3, no. 4, Dec, pp. 107–112, 2022, doi: 10.63282/3050-9262.IJAIDSML-V3I4P112.
[32] R. Duan, X. Liu, Z. Ding, and Y. Zhang, “Quantum-Inspired Fusion for Open-Domain Question Answering,” Electronics, vol. 13, no. 20, 2024, doi: 10.3390/electronics13204135.
[33] G. Maddali, “Enhancing Database Architectures with Artificial Intelligence (AI),” SSRN Electron. J., 2025, doi: 10.2139/ssrn.5276667.
[34] K. Ma, H. Cheng, Y. Zhang, X. Liu, E. Nyberg, and J. Gao, “Chain-of-skills: A configurable model for open-domain question answering,” arXiv Prepr. arXiv2305.03130, 2023.
[35] T. Zhang, D. Li, Q. Chen, C. Wang, and X. He, “BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering,” 2025. doi: 10.48550/arXiv.2505.11811.
[36] R. Patel, “Artificial Intelligence-Powered Optimization of Industrial IoT Networks Using Python-Based Machine Learning,” ESP J. Eng. Technol. Adv., vol. 3, no. 4, pp. 138–148, 2023, doi: 10.56472/25832646/JETA-V3I8P116.
[37] M. Zaib, W. E. Zhang, Q. Sheng, A. Mahmood, and Y. Zhang, “Conversational question answering: a survey,” Knowl. Inf. Syst., vol. 64, 2022, doi: 10.1007/s10115-022-01744-y.
[38] Q. Zhang et al., “A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models,” arxiv, pp. 1–27, 2025.
[39] M. Arslan, H. Ghanem, S. Munawar, and C. Cruz, “A Survey on RAG with LLMs,” Procedia Comput. Sci., vol. 246, pp. 3781–3790, 2024, doi: https://doi.org/10.1016/j.procs.2024.09.178.
[40] B. Saha, U. Saha, and M. Zubair Malik, “QuIM-RAG: Advancing Retrieval-Augmented Generation With Inverted Question Matching for Enhanced QA Performance,” IEEE Access, vol. 12, pp. 185401–185410, 2024, doi: 10.1109/ACCESS.2024.3513155.
[41] K. Roy et al., “QA-RAG: Leveraging Question and Answer-based Retrieved Chunk Re-Formatting for Improving Response Quality During Retrieval-augmented Generation,” Jul. 2024. doi: 10.20944/preprints202407.0376.v1.
[42] J. Gu and D. Qin, “An arXiv Paper Question-Answering System Based on Qwen and RAG,” in 2024 6th International Conference on Frontier Technologies of Information and Computer (ICFTIC), 2024, pp. 1354–1361. doi: 10.1109/ICFTIC64248.2024.10913101.
[43] Q. Zhang et al., “A Survey for Efficient Open Domain Question Answering,” Proc. Annu. Meet. Assoc. Comput. Linguist., vol. 1, pp. 14447–14465, 2023, doi: 10.18653/v1/2023.acl-long.808.
