A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges

TL;DR

This systematic review analyzes highly cited research on retrieval-augmented generation (RAG), summarizing techniques, metrics, and challenges, and providing insights into its effectiveness, limitations, and future research directions.

Contribution

It offers a comprehensive synthesis of recent RAG studies, highlighting methodological gaps and proposing future research priorities.

Findings

RAG effectively grounds language models in up-to-date information

Identifies key datasets, architectures, and evaluation practices in RAG research

Highlights limitations and challenges in current RAG methodologies

Abstract

This systematic review of the research literature on retrieval-augmented generation (RAG) provides a focused analysis of the most highly cited studies published between 2020 and May 2025. A total of 128 articles met our inclusion criteria. The records were retrieved from ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and the Digital Bibliography and Library Project (DBLP). RAG couples a neural retriever with a generative language model, grounding output in up-to-date, non-parametric memory while retaining the semantic generalisation stored in model weights. Guided by the PRISMA 2020 framework, we (i) specify explicit inclusion and exclusion criteria based on citation count and research questions, (ii) catalogue datasets, architectures, and evaluation practices, and (iii) synthesise empirical evidence on the effectiveness and limitations of RAG. To mitigate citation-lag bias, we applied a lower citation-count threshold to papers published in 2025 so that emerging breakthroughs with naturally fewer citations were still captured. This review clarifies the current research landscape, highlights methodological gaps, and charts priority directions for future research.