@inproceedings{chen-etal-2026-concise,
title = "Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation",
author = "Chen, Guo and
Li, Qiuyuan and
Li, Qiuxian and
Dai, Hongliang and
Chen, Xiang and
Li, Piji",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1082/",
pages = "24853--24868",
ISBN = "979-8-89176-459-0",
abstract = "In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. Existing citation generation methods for retrieval-augmented generation usually provide evidence at the paragraph or sentence level. Although such citations improve verifiability, they may still impose unnecessary reading burden on users: a cited sentence can contain irrelevant clauses, while an answer-bearing clause may lack sufficient contextual information such as the referred subject. In this paper, we study concise and sufficient sub-sentence citation generation, aiming to identify minimal yet self-contained evidence spans for answer verification. To this end, we first develop annotation guidelines for such citations and construct a corresponding dataset. To reduce annotation cost, we propose a data augmentation framework that generates synthetic citation annotations and filters low-quality instances using an evaluator model. Our experiments on the constructed dataset demonstrate that the proposed approach can generate high-quality and more readable citations. The code and data will be publicly released."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-concise">
<titleInfo>
<title>Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiuyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiuxian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongliang</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piji</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. Existing citation generation methods for retrieval-augmented generation usually provide evidence at the paragraph or sentence level. Although such citations improve verifiability, they may still impose unnecessary reading burden on users: a cited sentence can contain irrelevant clauses, while an answer-bearing clause may lack sufficient contextual information such as the referred subject. In this paper, we study concise and sufficient sub-sentence citation generation, aiming to identify minimal yet self-contained evidence spans for answer verification. To this end, we first develop annotation guidelines for such citations and construct a corresponding dataset. To reduce annotation cost, we propose a data augmentation framework that generates synthetic citation annotations and filters low-quality instances using an evaluator model. Our experiments on the constructed dataset demonstrate that the proposed approach can generate high-quality and more readable citations. The code and data will be publicly released.</abstract>
<identifier type="citekey">chen-etal-2026-concise</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1082/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>24853</start>
<end>24868</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation
%A Chen, Guo
%A Li, Qiuyuan
%A Li, Qiuxian
%A Dai, Hongliang
%A Chen, Xiang
%A Li, Piji
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F chen-etal-2026-concise
%X In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. Existing citation generation methods for retrieval-augmented generation usually provide evidence at the paragraph or sentence level. Although such citations improve verifiability, they may still impose unnecessary reading burden on users: a cited sentence can contain irrelevant clauses, while an answer-bearing clause may lack sufficient contextual information such as the referred subject. In this paper, we study concise and sufficient sub-sentence citation generation, aiming to identify minimal yet self-contained evidence spans for answer verification. To this end, we first develop annotation guidelines for such citations and construct a corresponding dataset. To reduce annotation cost, we propose a data augmentation framework that generates synthetic citation annotations and filters low-quality instances using an evaluator model. Our experiments on the constructed dataset demonstrate that the proposed approach can generate high-quality and more readable citations. The code and data will be publicly released.
%U https://aclanthology.org/2026.emnlp-main.1082/
%P 24853-24868
Markdown (Informal)
[Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation](https://aclanthology.org/2026.emnlp-main.1082/) (Chen et al., EMNLP 2026)
ACL