DuetRAG: Collaborative Retrieval-Augmented Generation

TL;DR

DuetRAG introduces a collaborative framework that jointly fine-tunes domain-specific retrieval and generation models to improve knowledge relevance and answer quality in complex, knowledge-intensive tasks.

Contribution

The paper presents DuetRAG, a novel approach that simultaneously fine-tunes retrieval and generation models for better domain knowledge integration in RAG systems.

Findings

DuetRAG matches expert human performance on HotPot QA.

Improved retrieval relevance leads to higher quality generated answers.

Joint training enhances knowledge accuracy in complex questions.

Abstract

Retrieval-Augmented Generation (RAG) methods augment the input of Large Language Models (LLMs) with relevant retrieved passages, reducing factual errors in knowledge-intensive tasks. However, contemporary RAG approaches suffer from irrelevant knowledge retrieval issues in complex domain questions (e.g., HotPot QA) due to the lack of corresponding domain knowledge, leading to low-quality generations. To address this issue, we propose a novel Collaborative Retrieval-Augmented Generation framework, DuetRAG. Our bootstrapping philosophy is to simultaneously integrate the domain fintuning and RAG models to improve the knowledge retrieval quality, thereby enhancing generation quality. Finally, we demonstrate DuetRAG' s matches with expert human researchers on HotPot QA.