Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation

2025-09-25 · Guo Chen, Qiuyuan Li, Qiuxian Li, Hongliang Dai, Xiang Chen, Piji Li arxiv

In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. However, we observe two problems in the citations produced by existing attribution methods. First, the citations are typically provided at the sentence or even paragraph level. Long sentences or paragraphs may include a substantial amount of irrelevant content. Second, sentence-level citations may omit information that is essential for verifying the output, forcing users to read the surrounding context. In this paper, we propose generating sub-sentence citations that are both concise and sufficient, thereby reducing the effort required by users to confirm the correctness of the generated output. To this end, we first develop annotation guidelines for such citations and construct a corresponding dataset. Then, we propose an attribution framework for generating citations that adhere to our standards. This framework leverages LLMs to automatically generate fine-tuning data for our task and employs a credit model to filter out low-quality examples. Our experiments on the constructed dataset demonstrate that the propose approach can generate high-quality and more readable citations.

📄 PDF Abstract BibTeX arXiv:2509.20859

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

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

2024-07-01 · Sirui Xia, Xintao Wang, Jiaqing Liang, Yifei Zhang 외

Retrieval-Augmented Generation (RAG) has been widely adopted to enhance Large Language Models (LLMs) in knowledge-intensive tasks. Recently, Attributed Text Generation (ATG) has attracted growing attention, which provide…

Fact Checking Long Form Question Answering Question Answering RAG+4

SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation

2025-10-17 · Ines Besrour, Jingbo He, Tobias Schreieder, Michael Färber arxiv

We present SQuAI (https://squai.scads.ai/), a scalable and trustworthy multi-agent retrieval-augmented generation (RAG) framework for scientific question answering (QA) with large language models (LLMs). SQuAI addresses …

Question Answering

Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG

2026-05-14 · Riccardo Terrenzi, Maximilian von Zastrow, Serkan Ayvaz arxiv

Retrieval-Augmented Generation can improve factuality by grounding answers in external evidence, but Agentic GraphRAG complicates what it means for citations to be faithful. In these systems, an agent explores a knowledg…

Attribute First, then Generate: Locally-attributable Grounded Text Generation

2024-03-25 · Aviv Slobodkin, Eran Hirsch, Arie Cattan, Tal Schuster 외

Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checkin…

Attribute Document Summarization Fact Checking Fact Verification+5

Candidate-Constrained Retrieval-Augmented Generation for LongEval-RAG: System Design and Empirical Analysis

2026-07-04 · Yingdong Yang, Haijian Wu arxiv

We present a candidate-constrained retrieval-augmented generation system for LongEval-RAG, where each query is associated with an organizer-provided candidate set and all retrieved evidence and final citations must remai…