English

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

Computation and Language 2025-05-26 v2

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%.

Keywords

Cite

@article{arxiv.2407.01796,
  title  = {Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation},
  author = {Sirui Xia and Xintao Wang and Jiaqing Liang and Yifei Zhang and Weikang Zhou and Jiaji Deng and Fei Yu and Yanghua Xiao},
  journal= {arXiv preprint arXiv:2407.01796},
  year   = {2025}
}

Comments

Accepted to NAACL 2025 Findings

R2 v1 2026-06-28T17:25:45.959Z