mlsanityData to 14 Oct 2026

Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction

arXiv 2508.18780 ↗First posted 26 Aug 2025cs.CL cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

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 state-of-the-art performance, with a notable increase in 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 32 references that are in the map. First posted on arXiv 26 Aug 2025.

Builds on

17 of 32 references.

References · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  8. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  9. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 963
  10. 2020GECToR -- Grammatical Error Correction: Tag, Not Rewritecited by 177
  11. 2025ToRL: Scaling Tool-Integrated RLcited by 169
  12. 2023Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluationcited by 97
5 more
  1. 2020Seq2Edits: Sequence Transduction Using Span-level Edit Operationscited by 58
  2. 2023Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistancecited by 33
  3. 2020Data Weighted Training Strategies for Grammatical Error Correctioncited by 26
  4. 2024Improving Grammatical Error Correction via Contextual Data Augmentationcited by 6
  5. 2023Evaluating the Capability of Large-scale Language Models on Chinese Grammatical Error Correction Taskcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CEC-Zero: Chinese Error Correction Solution Based on LLM
  2. 2026Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning
  3. 2024Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
  4. 2026CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
  5. 2024Training Language Models to Self-Correct via Reinforcement Learning
  6. 2025RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs
  7. 2024Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction
  8. 2026VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction