Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
Sirui Xia, Xintao Wang, Jiaqing Liang, Yifei Zhang, Weikang Zhou, Jiaji Deng, Fei Yu, Yanghua Xiao
Abstract
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%.
BibTeX
@inproceedings{xia-etal-2025-ground,
title = "Ground Every Sentence: Improving Retrieval-Augmented {LLM}s with Interleaved Reference-Claim Generation",
author = "Xia, Sirui and
Wang, Xintao and
Liang, Jiaqing and
Zhang, Yifei and
Zhou, Weikang and
Deng, Jiaji and
Yu, Fei and
Xiao, Yanghua",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.55/",
pages = "969--988",
ISBN = "979-8-89176-195-7"
}