DuetRAG: Collaborative Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiao, Dian, Cai, Li, Huang, Jingsheng, Zhang, Wenqiao, Tang, Siliang, Zhuang, Yueting
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909208061935616
author Jiao, Dian
Cai, Li
Huang, Jingsheng
Zhang, Wenqiao
Tang, Siliang
Zhuang, Yueting
author_facet Jiao, Dian
Cai, Li
Huang, Jingsheng
Zhang, Wenqiao
Tang, Siliang
Zhuang, Yueting
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13002
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DuetRAG: Collaborative Retrieval-Augmented Generation
Jiao, Dian
Cai, Li
Huang, Jingsheng
Zhang, Wenqiao
Tang, Siliang
Zhuang, Yueting
Computation and Language
Artificial Intelligence
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.
title DuetRAG: Collaborative Retrieval-Augmented Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.13002