English

Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction

Computation and Language 2025-08-27 v1 Artificial Intelligence

Abstract

Grammatical error correction is a significant task in NLP. Traditional methods based on encoder-decoder models have achieved certain success, but the application of LLMs in this field is still underexplored. Current research predominantly relies on supervised fine-tuning to train LLMs to directly generate the corrected sentence, which limits the model's powerful reasoning ability. To address this limitation, we propose a novel framework based on Rule-Based RL. Through experiments on the Chinese datasets, our Rule-Based RL framework achieves \textbf{state-of-the-art }performance, with a notable increase in \textbf{recall}. This result clearly highlights the advantages of using RL to steer LLMs, offering a more controllable and reliable paradigm for future development in GEC.

Keywords

Cite

@article{arxiv.2508.18780,
  title  = {Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction},
  author = {Yilin Li and Xunjian Yin and Yilin Chen and Xiaojun Wan},
  journal= {arXiv preprint arXiv:2508.18780},
  year   = {2025}
}

Comments

Code will be released upon publication

R2 v1 2026-07-01T05:05:59.461Z