FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems
This work addresses a tooling gap for researchers and practitioners working on RAG systems, but it is incremental as it builds on existing fine-tuning methods without introducing new algorithmic innovations.
The authors tackled the problem of fine-tuning retrieval-augmented generation (RAG) systems by introducing FedRAG, a framework that supports fine-tuning across centralized and federated architectures, offering a simple interface and seamless conversion between training tasks.
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.