@inproceedings{zhang-2026-training,
title = "A Training-Free Single-Pass Vision{--}Language Pipeline for Sentence-Level Visual {C}hinese Grammatical Error Correction",
author = "Zhang, Lexuan",
editor = "Wang, Xiaoman and
Wang, Qianyu and
Liu, Zhengyuan and
Chen, Nancy F. and
Yuan, Zheng and
Lan, Yunshi and
Jiang, Jing",
booktitle = "Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.multilll-1.9/",
pages = "77--83",
ISBN = "979-8-89176-449-1",
abstract = "Handwritten text by language learners couples recognition errors with grammatical errors, which makes automatic correction of such text harder than either subproblem alone. Visual Chinese grammatical error correction asks a system to read a handwritten sentence image and to emit both a fully corrected sentence and a list of localized visual edits. We describe a training-free pipeline that makes one call to a vision{--}language model (VLM) per image and jointly requests a verbatim transcription, a minimal-edit correction, and a typed bounding-box edit list in a single JSON object; a deterministic packer enforces schema and coverage, and a second engine fills only the test images for which the first produces no valid record. A paired 19-image development comparison under a proxy of the official $F_{0.5}$ metric finds that two VLMs obtain the same edit true-positive count while one emits nearly twice as many edits; the more conservative engine has higher edit precision on this slice. The system obtains an official score of 0.5905 on the hidden sentence-level test set of the VisCGEC-v2.0 shared task. The result suggests that a single-pass training-free VLM pipeline is viable for this task, and that edit precision is a useful engine-selection signal on the measured development slice."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-2026-training">
<titleInfo>
<title>A Training-Free Single-Pass Vision–Language Pipeline for Sentence-Level Visual Chinese Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lexuan</namePart>
<namePart type="family">Zhang</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 1st Workshop on Multi-modality and Multi-lingual Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoman</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunshi</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-449-1</identifier>
</relatedItem>
<abstract>Handwritten text by language learners couples recognition errors with grammatical errors, which makes automatic correction of such text harder than either subproblem alone. Visual Chinese grammatical error correction asks a system to read a handwritten sentence image and to emit both a fully corrected sentence and a list of localized visual edits. We describe a training-free pipeline that makes one call to a vision–language model (VLM) per image and jointly requests a verbatim transcription, a minimal-edit correction, and a typed bounding-box edit list in a single JSON object; a deterministic packer enforces schema and coverage, and a second engine fills only the test images for which the first produces no valid record. A paired 19-image development comparison under a proxy of the official F₀.5 metric finds that two VLMs obtain the same edit true-positive count while one emits nearly twice as many edits; the more conservative engine has higher edit precision on this slice. The system obtains an official score of 0.5905 on the hidden sentence-level test set of the VisCGEC-v2.0 shared task. The result suggests that a single-pass training-free VLM pipeline is viable for this task, and that edit precision is a useful engine-selection signal on the measured development slice.</abstract>
<identifier type="citekey">zhang-2026-training</identifier>
<location>
<url>https://aclanthology.org/2026.multilll-1.9/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>77</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Training-Free Single-Pass Vision–Language Pipeline for Sentence-Level Visual Chinese Grammatical Error Correction
%A Zhang, Lexuan
%Y Wang, Xiaoman
%Y Wang, Qianyu
%Y Liu, Zhengyuan
%Y Chen, Nancy F.
%Y Yuan, Zheng
%Y Lan, Yunshi
%Y Jiang, Jing
%S Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-449-1
%F zhang-2026-training
%X Handwritten text by language learners couples recognition errors with grammatical errors, which makes automatic correction of such text harder than either subproblem alone. Visual Chinese grammatical error correction asks a system to read a handwritten sentence image and to emit both a fully corrected sentence and a list of localized visual edits. We describe a training-free pipeline that makes one call to a vision–language model (VLM) per image and jointly requests a verbatim transcription, a minimal-edit correction, and a typed bounding-box edit list in a single JSON object; a deterministic packer enforces schema and coverage, and a second engine fills only the test images for which the first produces no valid record. A paired 19-image development comparison under a proxy of the official F₀.5 metric finds that two VLMs obtain the same edit true-positive count while one emits nearly twice as many edits; the more conservative engine has higher edit precision on this slice. The system obtains an official score of 0.5905 on the hidden sentence-level test set of the VisCGEC-v2.0 shared task. The result suggests that a single-pass training-free VLM pipeline is viable for this task, and that edit precision is a useful engine-selection signal on the measured development slice.
%U https://aclanthology.org/2026.multilll-1.9/
%P 77-83
Markdown (Informal)
[A Training-Free Single-Pass Vision–Language Pipeline for Sentence-Level Visual Chinese Grammatical Error Correction](https://aclanthology.org/2026.multilll-1.9/) (Zhang, Multi-LLL 2026)
ACL