一作ACL 2026Poster· Natural Language Processing
CSRP : Chain-of-Thought Reasoning for C hinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
Wei Tian · Yuhao Zhou · Man Lan
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 f...