Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Sirui, Wang, Xintao, Liang, Jiaqing, Zhang, Yifei, Zhou, Weikang, Deng, Jiaji, Yu, Fei, Xiao, Yanghua
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908375757881344
author Xia, Sirui
Wang, Xintao
Liang, Jiaqing
Zhang, Yifei
Zhou, Weikang
Deng, Jiaji
Yu, Fei
Xiao, Yanghua
author_facet Xia, Sirui
Wang, Xintao
Liang, Jiaqing
Zhang, Yifei
Zhou, Weikang
Deng, Jiaji
Yu, Fei
Xiao, Yanghua
contents Retrieval-Augmented Generation (RAG) has been widely adopted to enhance Large Language Models (LLMs) in knowledge-intensive tasks. To enhance credibility and verifiability in RAG systems, Attributed Text Generation (ATG) is proposed, which provides citations to retrieval knowledge in LLM-generated responses. Prior methods mainly adopt coarse-grained attributions, with passage-level or paragraph-level references or citations, which fall short in verifiability. This paper proposes ReClaim (Refer & Claim), a fine-grained ATG method that alternates the generation of references and answers step by step. Different from previous coarse-grained attribution, ReClaim provides sentence-level citations in long-form question-answering tasks. With extensive experiments, we verify the effectiveness of ReClaim in extensive settings, achieving a citation accuracy rate of 90%.
format Preprint
id arxiv_https___arxiv_org_abs_2407_01796
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
Xia, Sirui
Wang, Xintao
Liang, Jiaqing
Zhang, Yifei
Zhou, Weikang
Deng, Jiaji
Yu, Fei
Xiao, Yanghua
Computation and Language
Retrieval-Augmented Generation (RAG) has been widely adopted to enhance Large Language Models (LLMs) in knowledge-intensive tasks. To enhance credibility and verifiability in RAG systems, Attributed Text Generation (ATG) is proposed, which provides citations to retrieval knowledge in LLM-generated responses. Prior methods mainly adopt coarse-grained attributions, with passage-level or paragraph-level references or citations, which fall short in verifiability. This paper proposes ReClaim (Refer & Claim), a fine-grained ATG method that alternates the generation of references and answers step by step. Different from previous coarse-grained attribution, ReClaim provides sentence-level citations in long-form question-answering tasks. With extensive experiments, we verify the effectiveness of ReClaim in extensive settings, achieving a citation accuracy rate of 90%.
title Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
topic Computation and Language
url https://arxiv.org/abs/2407.01796