FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems

Val Andrei Fajardo, D. B. Emerson, Amandeep Singh, Marcelo Lotif, Veronica Chatrath, Izuki Matsuba, Chi Ho Cheung, Ravi Theja Desetty

Keywords: Retrieval-augmented generation, LLMs, Fine-tuning, Federated learning, Open-source

TL;DR: FedRAG — a new framework for fine-tuning RAG systems across centralized or federated architectures

Abstract: 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.

Submission Number: 36