CSRP：基于效率感知奖励的强化学习链式推理中文文本纠错
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
AI总结：
提出CSRP三阶段框架，通过连续预训练、链式推理监督微调和基于效率感知奖励的组相对策略优化，在NACGEC基准上实现最优性能，有效缓解过度纠正偏差。
摘要：
基于大语言模型的中文语法纠错系统面临两个关键挑战：通用模型缺乏针对细微语法区别的专业语言先验，以及使用最大似然估计的监督微调无法优化以精度为中心的指标，导致系统性过度纠正。我们提出CSRP，一个三阶段框架，通过以下步骤逐步构建纠错能力：在590万平衡样本上进行连续预训练以内化领域知识，使用显式错误推理进行链式推理监督微调以实现诊断透明度，以及采用新颖的效率感知奖励进行组相对策略优化，明确惩罚不必要的编辑。在NACGEC基准上，CSRP以50.99的$F_{0.5}$和57.17的精确率实现了最先进性能，大幅优于先前最佳结果，同时有效缓解了MLE训练模型固有的过度纠正偏差。我们的方法还将CSCD拼写纠错提升至59.61的F1，超过GPT-4 5.20分。全面的消融研究表明，RL对齐阶段相比SFT基线贡献了8%的相对增益，且该增益与大规模CPT的贡献正交，验证了针对编辑效率的显式优化对于高质量语法纠错至关重要。我们的代码可在https://github.com/TW-NLP/ChineseErrorCorrector获取。
英文摘要：
Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critical challenges: general-purpose models lack specialized linguistic priors for subtle grammatical distinctions, and Supervised Fine-Tuning (SFT) with Maximum Likelihood Estimation fails to optimize for precision-focused metrics, leading to systematic over-correction. We propose CSRP, a three-stage framework that progressively builds correction capability through Continual Pre-training (CPT) on 5.9M balanced samples to internalize domain knowledge, Chain-of-Thought SFT with explicit error reasoning for diagnostic transparency, and Group Relative Policy Optimization with a novel Efficiency-Aware Reward that explicitly penalizes unnecessary edits. On the NACGEC benchmark, CSRP achieves state-of-the-art performance with 50.99 $F_{0.5}$ and 57.17 precision, substantially outperforming previous best results while effectively mitigating the over-correction bias inherent in MLE-trained models. Our method also advances CSCD spelling correction to 59.61 F1, surpassing GPT-4 by 5.20 points. Comprehensive ablation studies demonstrate that the RL alignment stage contributes a 8\% relative gain over the SFT baseline, and that this gain is orthogonal to the contribution of large-scale CPT, validating that explicit optimization for edit efficiency is essential for high-quality grammatical error correction. Our code is available at https://github.com/TW-NLP/ChineseErrorCorrector.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
