从图片到定位修改:手写中文作文语法纠错真实场景基准 G-CGEC-Eval
From Images to Grounded Edits: A Real-World Benchmark for Chinese Grammatical Error Correction in Handwritten Essays
AI 导读
研究者提出图像到定位修改的任务 G-CGEC 及配套基准 G-CGEC-Eval,要求模型在 K-12 手写中文作文图片上同时预测语法纠错及其位置,并采用基于 IoU 和中心距离匹配的评测指标。
正文 · 原文
Abstract:Chinese Grammatical Error Correction (CGEC) is typically formulated as a text-to-text problem. While suitable for digital texts, this formulation falls short in real-world K-12 education, where AI-assisted corrections are expected directly on essay images, which are primarily handwritten and exhibit many irregularities. To bridge this gap, we introduce Grounded Chinese Grammatical Error Correction (G-CGEC), an image-to-grounded-edit task requiring systems to predict both corrections and their positions on essay images. We propose G-CGEC-Eval, a benchmark comprising real-world images of K-12 Chinese essays with fine-grained annotations. For evaluation, we adapt IoU-based metrics from object detection and propose a more tolerant alternative based on center-distance matching. Using this benchmark, we evaluate open-source and proprietary vision-language models under a direct single-pass setting, as well as settings with auxiliary components (OCR and character grounding) coordinated via pipelining or agentic harnessing. Results show that even top-tier proprietary models perform surprisingly poorly in the single-pass setting, while pipelining and agentic harnessing yield meaningful improvements. Notably, an error-type-based multi-agent workflow achieves the best performance, establishing it as the strongest baseline for future G-CGEC research. Through ablations and fine-grained analysis, we find the task remains far from solved, with linguistic error discovery and character-level grounding as the primary bottlenecks. This underscores the need for models that better integrate visual perception with linguistic reasoning and visual grounding.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.17966 [cs.CV] |
| (or arXiv:2611.17966v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17966 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuzhong Hong [view email]
[v1]
Fri, 13 Nov 2026 09:55:57 UTC (3,037 KB)
来源:arXiv cs.AI · arxiv.org