A Systematic Literature Review of Retrieval-Augmented Generation: Methods, Applications, and Future Research Directions
Abstract
Retrieval-Augmented Generation (RAG) represents a growing research direction in the advancement of large language models (LLMs) by incorporating external information sources into the response generation process. As LLM-based systems are increasingly deployed in information-sensitive domains such as healthcare, education, and law, the demand for responses that are not only fluent but also verifiable and context-aware has become more pronounced. This study conducts a systematic literature review (SLR) of 100 recent publications to examine methodological approaches, application domains, technical challenges, and research contributions related to RAG. The review draws on studies indexed in major academic databases, including IEEE, ACM, and Springer, and applies structured inclusion and exclusion criteria to ensure analytical rigor. The findings reveal a strong emphasis on architectural optimization, particularly in the interaction between retrieval and generation components, alongside widespread adoption in domain-specific contexts. Persistent challenges identified across the literature include limitations in retriever effectiveness, system integration complexity, and the absence of standardized evaluation benchmarks. Overall, this review provides a structured synthesis of current RAG research and highlights directions for future investigation and practical deployment..
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.