CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards

• URL: http://arxiv.org/abs/2606.00020v1
• Date: Tue, 14 Apr 2026 02:06:38 GMT
• Title: CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
• Abstract summary: General-purpose Chinese language models lack specialized linguistic priors for subtle grammatical distinctions.<n>Supervised Fine-Tuning (SFT) with Maximum Likelihood Estimation fails to optimize for precision-focused metrics.<n>We propose CSRP, a three-stage framework that progressively builds correction capability through Continual Pre-training (CPT) on 5.9M balanced samples.<n>On the NACGEC benchmark, CSRP achieves state-of-the-art performance with 50.99 $F_0.5$ and 57.17 precision.
• Score: 20.028937245593003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards [73.44333771806282]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models.<n>We propose Correction-Oriented Policy Optimization (CIPO), a simple and effective extension to RLVR that converts on-policy failed trajectories into correction-oriented supervision.<n>CIPO improves learning effectiveness while explicitly enhancing the model's ability to correct its own errors.
  arXiv  Detail & Related papers  (2026-05-14T08:22:21Z)
• Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation [68.85147984815778]
  We propose EA-RLVR (Entity-Anchored Reinforcement Learning with Verifiable Rewards) to incentivize the effective use of parametric knowledge.<n>EA-RLVR anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization.<n>We evaluate EA-RLVR on XC-Translate and observe consistent improvements in both entity translation accuracy and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-04-18T07:15:43Z)
• How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding [4.852493246050006]
  Large language models (LLMs) generate outputs autoregressively, leading to inevitable output uncertainty.<n>We propose Log-Scale Focal Uncertainty (LSFU), a first-token-based metric inspired by focal loss.<n>We show UCPOF improves average accuracy by 6.03% over few-shot baselines, surpasses always-on full RAG by 5.75%, and reduces the average retrieval trigger rate by 50.66%.
  arXiv  Detail & Related papers  (2026-02-23T11:55:14Z)
• Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models [0.0]
  We introduce RLTT (Reward Latent Thought Trajectories), a reinforcement learning framework which distributes reward across the full latent reasoning trajectory.<n> RLTT yields substantial improvements over GRPO on challenging mathematical reasoning benchmarks, improving accuracy by +14.4% on MATH-500, +16.6% on AIME24, and +10.0% on BeyondAIME.<n>Despite being trained exclusively on mathematics, RLTT also transfers effectively to non-mathematical reasoning benchmarks, demonstrating the effectiveness of trajectory-level credit assignment for reinforcement learning in LoopLMs.
  arXiv  Detail & Related papers  (2026-02-11T04:39:42Z)
• Dual Decomposition of Weights and Singular Value Low Rank Adaptation [9.048461365342204]
  We propose DuDe, a novel approach that decomposes weight matrices into magnitude and direction components.<n>Our evaluation demonstrates DuDe's superior performance and robustness, achieving up to 48.35% accuracy on MMLU and 62.53% ($pm$ 1.59) accuracy on GSM8K.
  arXiv  Detail & Related papers  (2025-05-20T13:49:15Z)
• MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities [0.0]
  We propose a novel framework, Mixture of Losses (MoL), which decouples optimization objectives for domain-specific and general corpora.<n>Specifically, cross-entropy (CE) loss is applied to domain-corpus to ensure knowledge acquisition, while Kullback-Leibler (KL) divergence aligns general-corpus training with the base model's foundational capabilities.
  arXiv  Detail & Related papers  (2025-05-17T15:12:47Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• Optimizing Language Models for Grammatical Acceptability: A Comparative Study of Fine-Tuning Techniques [0.0]
  This study explores the fine-tuning (FT) of the Open Pre-trained Transformer (OPT-125M) for grammatical tasks using the CoLA dataset.
  arXiv  Detail & Related papers  (2025-01-14T05:41:09Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Parameter-Efficient Learning for Text-to-Speech Accent Adaptation [58.356667204518985]
  This paper presents a parameter-efficient learning (PEL) to develop a low-resource accent adaptation for text-to-speech (TTS) A resource-efficient adaptation from a frozen pre-trained TTS model is developed by using only 1.2% to 0.8% of original trainable parameters. Experiment results show that the proposed methods can achieve competitive naturalness with parameter-efficient decoder fine-tuning.
  arXiv  Detail & Related papers  (2023-05-18T22:02:59Z)
• Optimizing Two-way Partial AUC with an End-to-end Framework [154.47590401735323]
  Area Under the ROC Curve (AUC) is a crucial metric for machine learning. Recent work shows that the TPAUC is essentially inconsistent with the existing Partial AUC metrics. We present the first trial in this paper to optimize this new metric.
  arXiv  Detail & Related papers  (2022-06-23T12:21:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.