{"ID":2877976,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.18780","arxiv_id":"2508.18780","title":"Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction","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.","short_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...","url_abs":"https://arxiv.org/abs/2508.18780","url_pdf":"https://arxiv.org/pdf/2508.18780v1","authors":"[\"Yilin Li\",\"Xunjian Yin\",\"Yilin Chen\",\"Xiaojun Wan\"]","published":"2025-08-26T08:04:04Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}