Edit-Wise Preference Optimization for Grammatical Error Correction

Jiehao Liang, Haihui Yang, Shiping Gao, Xiaojun Quan


Abstract
While large language models (LLMs) have achieved remarkable success in various natural language processing tasks, their strengths have yet to be fully demonstrated in grammatical error correction (GEC). This is partly due to the misalignment between their pre-training objectives and the GEC principle of making minimal edits. In this work, we aim to bridge this gap by introducing a novel method called Edit-wise Preference Optimization (EPO). By distinguishing the importance of different tokens and assigning higher reward weights to edit tokens during preference optimization, our method captures fine-grained distinctions in GEC that traditional preference learning often overlooks. Extensive experiments on both English and Chinese datasets show that our framework consistently outperforms strong baselines, achieving state-of-the-art performance and demonstrating the advantages of LLMs in GEC.
Anthology ID:
2025.coling-main.229
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3401–3414
Language:
URL:
https://aclanthology.org/2025.coling-main.229/
DOI:
Bibkey:
Cite (ACL):
Jiehao Liang, Haihui Yang, Shiping Gao, and Xiaojun Quan. 2025. Edit-Wise Preference Optimization for Grammatical Error Correction. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3401–3414, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Edit-Wise Preference Optimization for Grammatical Error Correction (Liang et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.229.pdf