PrefRAG: Preference-Driven Multi-Source Retrieval Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Qingfei, Wang, Ruobing, Cen, Yukuo, Zha, Daren, Tan, Shicheng, Tang, Jie
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913779495731200
author Zhao, Qingfei
Wang, Ruobing
Cen, Yukuo
Zha, Daren
Tan, Shicheng
Tang, Jie
author_facet Zhao, Qingfei
Wang, Ruobing
Cen, Yukuo
Zha, Daren
Tan, Shicheng
Tang, Jie
contents Retrieval-Augmented Generation (RAG) has emerged as a reliable external knowledge augmentation technique to mitigate hallucination issues and parameterized knowledge limitations in Large Language Models (LLMs). Existing adaptive RAG (ARAG) systems excel at in-depth exploration within a single source but struggle to effectively and controllably explore different retrieval sources, as they fail to foresee their internal knowledge features. We develop a novel multi-source ARAG system, PrefRAG, which enhances RAG by enabling in-depth and controllable exploration of diverse retrieval sources through preference-driven adaptive retrieval and self-reflection. PrefRAG first fully explores controllable local sources in adaptive retrieval and supplements with the web when appropriate, ultimately selecting the optimal source for knowledge observation. Subsequently, PrefRAG feeds answer quality feedback into the retrieval process, optimizing it from the generation perspective to produce higher-quality responses. Extensive experiments confirm its superiority, high retrieval efficiency, and knowledge controllability. PrefRAG outperforms Vanilla RAG and the leading MS-ARAG by up to 25.6% and 13.9% respectively. Additionally, PrefRAG trained with DPO achieves higher performance. The code and data are available at https://github.com/QingFei1/PrefRAG.git.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00689
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PrefRAG: Preference-Driven Multi-Source Retrieval Augmented Generation
Zhao, Qingfei
Wang, Ruobing
Cen, Yukuo
Zha, Daren
Tan, Shicheng
Tang, Jie
Computation and Language
Retrieval-Augmented Generation (RAG) has emerged as a reliable external knowledge augmentation technique to mitigate hallucination issues and parameterized knowledge limitations in Large Language Models (LLMs). Existing adaptive RAG (ARAG) systems excel at in-depth exploration within a single source but struggle to effectively and controllably explore different retrieval sources, as they fail to foresee their internal knowledge features. We develop a novel multi-source ARAG system, PrefRAG, which enhances RAG by enabling in-depth and controllable exploration of diverse retrieval sources through preference-driven adaptive retrieval and self-reflection. PrefRAG first fully explores controllable local sources in adaptive retrieval and supplements with the web when appropriate, ultimately selecting the optimal source for knowledge observation. Subsequently, PrefRAG feeds answer quality feedback into the retrieval process, optimizing it from the generation perspective to produce higher-quality responses. Extensive experiments confirm its superiority, high retrieval efficiency, and knowledge controllability. PrefRAG outperforms Vanilla RAG and the leading MS-ARAG by up to 25.6% and 13.9% respectively. Additionally, PrefRAG trained with DPO achieves higher performance. The code and data are available at https://github.com/QingFei1/PrefRAG.git.
title PrefRAG: Preference-Driven Multi-Source Retrieval Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2411.00689