Federated Retrieval-Augmented Generation: A Systematic Mapping Study

TL;DR

This paper systematically maps the emerging field of Federated Retrieval-Augmented Generation, analyzing its research trends, architectural patterns, and key challenges to guide future developments in privacy-preserving NLP.

Contribution

It is the first comprehensive systematic mapping study of Federated RAG, classifying research focuses, contributions, and identifying open challenges in the field.

Findings

Identifies key architectural patterns and trends in Federated RAG research.

Highlights privacy, heterogeneity, and evaluation as main challenges.

Provides a structured overview to guide future research directions.

Abstract

Federated Retrieval-Augmented Generation (Federated RAG) combines Federated Learning (FL), which enables distributed model training without exposing raw data, with Retrieval-Augmented Generation (RAG), which improves the factual accuracy of language models by grounding outputs in external knowledge. As large language models are increasingly deployed in privacy-sensitive domains such as healthcare, finance, and personalized assistance, Federated RAG offers a promising framework for secure, knowledge-intensive natural language processing (NLP). To the best of our knowledge, this paper presents the first systematic mapping study of Federated RAG, covering literature published between 2020 and 2025. Following Kitchenham's guidelines for evidence-based software engineering, we develop a structured classification of research focuses, contribution types, and application domains. We analyze architectural patterns, temporal trends, and key challenges, including privacy-preserving retrieval, cross-client heterogeneity, and evaluation limitations. Our findings synthesize a rapidly evolving body of research, identify recurring design patterns, and surface open questions, providing a foundation for future work at the intersection of RAG and federated systems.