CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kai, Jian, Zhang, Zidong, Chen, Jiwen, Wu, Zhengxiang, Sun, Songtao, Li, Fuyang, Cao, Yang, Liu, Qiang
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910034943803392
author Kai, Jian
Zhang, Zidong
Chen, Jiwen
Wu, Zhengxiang
Sun, Songtao
Li, Fuyang
Cao, Yang
Liu, Qiang
author_facet Kai, Jian
Zhang, Zidong
Chen, Jiwen
Wu, Zhengxiang
Sun, Songtao
Li, Fuyang
Cao, Yang
Liu, Qiang
contents Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. However, in paragraph-level Chinese professional writing, linguistic (word/grammar/punctuation) and factual errors frequently co-occur and interact, making unified correction both necessary and challenging. 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 generalization of specialized correction models, 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 Error within the same context outperform decoupled processes, and that agentic workflows can be effective with suitable backbone models. Overall, our dataset and empirical findings provide guidance for building reliable, fully automatic proofreading systems in industrial settings.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23845
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing
Kai, Jian
Zhang, Zidong
Chen, Jiwen
Wu, Zhengxiang
Sun, Songtao
Li, Fuyang
Cao, Yang
Liu, Qiang
Computation and Language
Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. However, in paragraph-level Chinese professional writing, linguistic (word/grammar/punctuation) and factual errors frequently co-occur and interact, making unified correction both necessary and challenging. 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 generalization of specialized correction models, 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 Error within the same context outperform decoupled processes, and that agentic workflows can be effective with suitable backbone models. Overall, our dataset and empirical findings provide guidance for building reliable, fully automatic proofreading systems in industrial settings.
title CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing
topic Computation and Language
url https://arxiv.org/abs/2602.23845