Applying GRPO with a rule-based, reference-match reward to a Qwen3-8B model after reasoning-augmented SFT achieves state-of-the-art F0.5 on Chinese GEC benchmark FCGEC and improves recall.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction
Applying GRPO with a rule-based, reference-match reward to a Qwen3-8B model after reasoning-augmented SFT achieves state-of-the-art F0.5 on Chinese GEC benchmark FCGEC and improves recall.