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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fajardo, Val Andrei, Emerson, David B., Singh, Amandeep, Chatrath, Veronica, Lotif, Marcelo, Theja, Ravi, Cheung, Alex, Matsuba, Izuki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915338734534656
author Fajardo, Val Andrei
Emerson, David B.
Singh, Amandeep
Chatrath, Veronica
Lotif, Marcelo
Theja, Ravi
Cheung, Alex
Matsuba, Izuki
author_facet Fajardo, Val Andrei
Emerson, David B.
Singh, Amandeep
Chatrath, Veronica
Lotif, Marcelo
Theja, Ravi
Cheung, Alex
Matsuba, Izuki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems
Fajardo, Val Andrei
Emerson, David B.
Singh, Amandeep
Chatrath, Veronica
Lotif, Marcelo
Theja, Ravi
Cheung, Alex
Matsuba, Izuki
Machine Learning
Computation and Language
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.
title FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2506.09200