Mapping the intersection of retrieval-augmented generation and knowledge graphs: A bibliometric review (2021–2026)

Abstract

Objective. The objective of this study was to provide a comprehensive bibliometric review of research at the intersection of retrieval-augmented generation (RAG) and knowledge graphs (KGs), to map the intellectual structure of the field, and to quantify scholarly activity on system architectures, evaluation venues, and emerging application domains from 2021 to 2026. Design/Methodology/Approach. A bibliometric review was conducted in accordance with the PRISMA 2020 reporting framework. A combined Scopus and Web of Science (WoS) search yielded 1,604 records (Scopus, n = 1,098; WoS, n = 506). After the removal of 444 cross-database duplicates using the KKU-BiblioMerge toolkit and the screening of 1,604 unique records against four exclusion criteria, 313 records were excluded, leaving 1,291 publications for analysis. A variety of bibliometric techniques were employed in the analysis, including descriptive bibliometrics, co-authorship analysis, country collaboration mapping, keyword co-occurrence, thematic mapping, co-citation analysis, and latent Dirichlet allocation topic modeling (k = 8, u_mass coherence = −1.46). The analyses were conducted in Python, utilizing the libraries pandas, NetworkX, and gensim. Results/Discussion. The findings indicated a rapid expansion of the field, with annual publication output increasing from 1 paper in 2021 to 700 papers in 2025 (average annual growth rate (AGR) of 235.49%). When author affiliations were aggregated at the unique-publication level and the two WoS variants “China” and “Peoples R China” were merged, Mainland China (n = 485 publications) and the United States (n = 139) emerged as the leading contributors. The most-cited publication was “Knowledge Graph Prompting for Multi-Document Question Answering,” with 110 citations. A total of eight major thematic clusters were identified, with “Retrieval-Augmented Generation Systems” and “Embedding & Semantic Representation” demonstrating the highest average citation impact. The findings suggested a growing scholarly focus on GraphRAG architectures and KG-enhanced large language model pipelines to enhance factual accuracy and knowledge grounding. Conclusions. Research on the integration of RAG and KGs is rapidly maturing and consolidating around hybrid architectures that combine structured knowledge retrieval with neural text generation. However, significant challenges persist, particularly regarding standardized evaluation benchmarks, cross-lingual RAG–KG systems, and scalable metadata generation frameworks. Originality/Value. This study offers the inaugural comprehensive bibliometric review of the RAG–KG research landscape. It provides a comprehensive intellectual framework for the field, identifies emerging research directions, and offers practical insights for the development of intelligent metadata-generation assistants and knowledge-enhanced AI systems.