Retrieval-augmented generation (RAG) systems have been shown to be effective in addressing many of the drawbacks of relying solely on the parametric memory of large language models. Recent work has demonstrated that RAG systems can be improved via fine-tuning of their retriever and generator models. In this work, we introduce FedRAG, a framework for fine-tuning RAG systems across centralized and federated architectures. FedRAG supports state-of-the-art fine-tuning methods, offering a simple and intuitive interface and a seamless conversion from centralized to federated training tasks. FedRAG is also deeply integrated with the modern RAG ecosystem, filling a critical gap in available tools.
@article{arxiv.2506.09200,
title = {FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems},
author = {Val Andrei Fajardo and David B. Emerson and Amandeep Singh and Veronica Chatrath and Marcelo Lotif and Ravi Theja and Alex Cheung and Izuki Matsuba},
journal= {arXiv preprint arXiv:2506.09200},
year = {2025}
}
Comments
9 pages, 4 figures, 2 tables. Accepted for the CODEML Workshop at ICML 2025. Framework code available at https://github.com/VectorInstitute/fed-rag