DuetRAG: Collaborative Retrieval-Augmented Generation
This addresses retrieval issues in RAG for domain-specific applications, offering a solution that is incremental by integrating domain fine-tuning with existing RAG models.
The paper tackles the problem of irrelevant knowledge retrieval in Retrieval-Augmented Generation (RAG) for complex domain questions like HotPot QA, resulting in a framework that matches expert human performance on this task.
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.