@inproceedings{kai-etal-2026-clfec,
title = "{CLFEC}: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level {C}hinese Professional Writing",
author = "Kai, Jian and
Zhang, Zidong and
Chen, Jiwen and
Wu, Zhengxiang and
Sun, Songtao and
Li, Fuyang and
Cao, Yang and
Liu, Qiang",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.41/",
pages = "849--878",
ISBN = "979-8-89176-439-2",
abstract = "Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. In paragraph-level Chinese professional writing, linguistic (word/grammar/punctuation) and factual errors can co-occur and interact. Moreover, editorial review leaves few observable errors in published professional texts, making controlled benchmark construction important. This paper introduces **CLFEC (Chinese Linguistic {\&} Factual Error Correction)**, a new task for joint linguistic and factual correction. We construct a mixed, multi-domain Chinese professional writing dataset spanning current affairs, finance, law, and medicine. We then conduct a systematic study of LLM-based correction paradigms, from prompting to retrieval-augmented generation (RAG) and agentic workflows. The analysis reveals practical challenges, including limited transfer of a specialized corrector, the need for evidence grounding for factual repair, the difficulty of mixed-error paragraphs, and over-correction on clean inputs. Results further show that handling linguistic and factual errors within the same context outperforms decoupled pipelines, and that agentic workflows can be effective with suitable backbone models. Overall, CLFEC provides a new benchmark for Chinese text correction research and practical guidance for proofreading systems. The dataset is publicly available at [https://github.com/jiu2021/CLFEC-Dataset](https://github.com/jiu2021/CLFEC-Dataset)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kai-etal-2026-clfec">
<titleInfo>
<title>CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Kai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zidong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiwen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengxiang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songtao</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. In paragraph-level Chinese professional writing, linguistic (word/grammar/punctuation) and factual errors can co-occur and interact. Moreover, editorial review leaves few observable errors in published professional texts, making controlled benchmark construction important. This paper introduces **CLFEC (Chinese Linguistic & Factual Error Correction)**, a new task for joint linguistic and factual correction. We construct a mixed, multi-domain Chinese professional writing dataset spanning current affairs, finance, law, and medicine. We then conduct a systematic study of LLM-based correction paradigms, from prompting to retrieval-augmented generation (RAG) and agentic workflows. The analysis reveals practical challenges, including limited transfer of a specialized corrector, the need for evidence grounding for factual repair, the difficulty of mixed-error paragraphs, and over-correction on clean inputs. Results further show that handling linguistic and factual errors within the same context outperforms decoupled pipelines, and that agentic workflows can be effective with suitable backbone models. Overall, CLFEC provides a new benchmark for Chinese text correction research and practical guidance for proofreading systems. The dataset is publicly available at [https://github.com/jiu2021/CLFEC-Dataset](https://github.com/jiu2021/CLFEC-Dataset).</abstract>
<identifier type="citekey">kai-etal-2026-clfec</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.41/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>849</start>
<end>878</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing
%A Kai, Jian
%A Zhang, Zidong
%A Chen, Jiwen
%A Wu, Zhengxiang
%A Sun, Songtao
%A Li, Fuyang
%A Cao, Yang
%A Liu, Qiang
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F kai-etal-2026-clfec
%X Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. In paragraph-level Chinese professional writing, linguistic (word/grammar/punctuation) and factual errors can co-occur and interact. Moreover, editorial review leaves few observable errors in published professional texts, making controlled benchmark construction important. This paper introduces **CLFEC (Chinese Linguistic & Factual Error Correction)**, a new task for joint linguistic and factual correction. We construct a mixed, multi-domain Chinese professional writing dataset spanning current affairs, finance, law, and medicine. We then conduct a systematic study of LLM-based correction paradigms, from prompting to retrieval-augmented generation (RAG) and agentic workflows. The analysis reveals practical challenges, including limited transfer of a specialized corrector, the need for evidence grounding for factual repair, the difficulty of mixed-error paragraphs, and over-correction on clean inputs. Results further show that handling linguistic and factual errors within the same context outperforms decoupled pipelines, and that agentic workflows can be effective with suitable backbone models. Overall, CLFEC provides a new benchmark for Chinese text correction research and practical guidance for proofreading systems. The dataset is publicly available at [https://github.com/jiu2021/CLFEC-Dataset](https://github.com/jiu2021/CLFEC-Dataset).
%U https://aclanthology.org/2026.aacl-long.41/
%P 849-878
Markdown (Informal)
[CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing](https://aclanthology.org/2026.aacl-long.41/) (Kai et al., AACL-IJCNLP 2026)
ACL
- Jian Kai, Zidong Zhang, Jiwen Chen, Zhengxiang Wu, Songtao Sun, Fuyang Li, Yang Cao, and Qiang Liu. 2026. CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 849–878, Hengqin, China. Association for Computational Linguistics.