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

TL;DR

This paper introduces CLFEC, a new task for jointly correcting linguistic and factual errors in paragraph-level Chinese professional writing, supported by a new dataset and empirical analysis of correction paradigms.

Contribution

It presents the CLFEC task, constructs a multi-domain dataset, and systematically evaluates LLM-based correction methods for unified linguistic and factual error correction.

Findings

Unified correction outperforms decoupled methods.

Agentic workflows are effective with suitable models.

Challenges include limited generalization and evidence grounding.

Abstract

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.