@inproceedings{zhang-etal-2026-know,
title = "Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations",
author = "Zhang, Yichi and
Chen, Zhuo and
Guo, Lingbing and
Xu, Jun and
Sun, Mengshu and
Liu, Zhizhen and
Liang, Lei and
Zhang, Wen and
Chen, Huajun",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.867/",
pages = "18996--19011",
ISBN = "979-8-89176-390-6",
abstract = "Question answering (QA) with reference texts is a classic application scenario for large language models (LLMs), where high standards for the credibility and traceability of generated answers are crucial. Many existing approaches focus on generating multi-level citations linked to specific references within the answer, making it verifiable and trustworthy. However, they often overlook key challenges such as citation granularity, the awareness of unknown information, and the adoption of effective training strategies. In this paper, we introduce Knowledge-informed Citation (KFC), which addresses these issues through a novel data construction pipeline, a new benchmark, and an innovative training strategy. With approximately 42K samples spanning 19 distinct domains, KFC includes both traditional citations referencing known entity-level information and specialized citations referring to unknown knowledge in the given question. This structure provides a more granular approach to citations, guiding the model to recognize and explicitly indicate unknown information, thus enhancing the quality and credibility of the response. Additionally, we propose a self-correction paradigm, Self-KFC, designed to fine-tune LLMs by refining poorly cited answers into more accurate ones, making it particularly suitable for citation-dependent scenarios. We present comprehensive experimental results to demonstrate the effectiveness and generalization of Self-KFC on the KFC benchmark."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-know">
<titleInfo>
<title>Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yichi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingbing</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengshu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhizhen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huajun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Question answering (QA) with reference texts is a classic application scenario for large language models (LLMs), where high standards for the credibility and traceability of generated answers are crucial. Many existing approaches focus on generating multi-level citations linked to specific references within the answer, making it verifiable and trustworthy. However, they often overlook key challenges such as citation granularity, the awareness of unknown information, and the adoption of effective training strategies. In this paper, we introduce Knowledge-informed Citation (KFC), which addresses these issues through a novel data construction pipeline, a new benchmark, and an innovative training strategy. With approximately 42K samples spanning 19 distinct domains, KFC includes both traditional citations referencing known entity-level information and specialized citations referring to unknown knowledge in the given question. This structure provides a more granular approach to citations, guiding the model to recognize and explicitly indicate unknown information, thus enhancing the quality and credibility of the response. Additionally, we propose a self-correction paradigm, Self-KFC, designed to fine-tune LLMs by refining poorly cited answers into more accurate ones, making it particularly suitable for citation-dependent scenarios. We present comprehensive experimental results to demonstrate the effectiveness and generalization of Self-KFC on the KFC benchmark.</abstract>
<identifier type="citekey">zhang-etal-2026-know</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.867/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>18996</start>
<end>19011</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations
%A Zhang, Yichi
%A Chen, Zhuo
%A Guo, Lingbing
%A Xu, Jun
%A Sun, Mengshu
%A Liu, Zhizhen
%A Liang, Lei
%A Zhang, Wen
%A Chen, Huajun
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F zhang-etal-2026-know
%X Question answering (QA) with reference texts is a classic application scenario for large language models (LLMs), where high standards for the credibility and traceability of generated answers are crucial. Many existing approaches focus on generating multi-level citations linked to specific references within the answer, making it verifiable and trustworthy. However, they often overlook key challenges such as citation granularity, the awareness of unknown information, and the adoption of effective training strategies. In this paper, we introduce Knowledge-informed Citation (KFC), which addresses these issues through a novel data construction pipeline, a new benchmark, and an innovative training strategy. With approximately 42K samples spanning 19 distinct domains, KFC includes both traditional citations referencing known entity-level information and specialized citations referring to unknown knowledge in the given question. This structure provides a more granular approach to citations, guiding the model to recognize and explicitly indicate unknown information, thus enhancing the quality and credibility of the response. Additionally, we propose a self-correction paradigm, Self-KFC, designed to fine-tune LLMs by refining poorly cited answers into more accurate ones, making it particularly suitable for citation-dependent scenarios. We present comprehensive experimental results to demonstrate the effectiveness and generalization of Self-KFC on the KFC benchmark.
%U https://aclanthology.org/2026.acl-long.867/
%P 18996-19011
Markdown (Informal)
[Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations](https://aclanthology.org/2026.acl-long.867/) (Zhang et al., ACL 2026)
ACL
- Yichi Zhang, Zhuo Chen, Lingbing Guo, Jun Xu, Mengshu Sun, Zhizhen Liu, Lei Liang, Wen Zhang, and Huajun Chen. 2026. Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 18996–19011, San Diego, California, United States. Association for Computational Linguistics.