# CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards

arXiv: https://arxiv.org/abs/2512.23971 · HTML: https://mlsanity.com/paper/2512.23971/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

## Builds on (most cited first, 19 of 19)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [Self-Evolving Curriculum for LLM Reasoning](https://mlsanity.com/paper/2505.14970/) (2025)
- [RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold](https://mlsanity.com/paper/2406.14532/) (2024)
- [Spelling Error Correction with Soft-Masked BERT](https://mlsanity.com/paper/2005.07421/) (2020)
- [NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space](https://mlsanity.com/paper/2309.14616/) (2023)
- [RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs](https://mlsanity.com/paper/2404.08555/) (2024)
- [On Designing Effective RL Reward at Training Time for LLM Reasoning](https://mlsanity.com/paper/2410.15115/) (2024)
- [Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding](https://mlsanity.com/paper/2502.06020/) (2025)
- [FT2TF: First-Person Statement Text-To-Talking Face Generation](https://mlsanity.com/paper/2312.05430/) (2023)
- [Swift Sampler: Efficient Learning of Sampler by 10 Parameters](https://mlsanity.com/paper/2410.05578/) (2024)
- [Prompt-Based Length Controlled Generation with Multiple Control Types](https://mlsanity.com/paper/2406.10278/) (2024)
- [Learning Musical Representations for Music Performance Question Answering](https://mlsanity.com/paper/2502.06710/) (2025)
- [Self-Evolved Reward Learning for LLMs](https://mlsanity.com/paper/2411.00418/) (2024)
- [Chinese Spelling Correction as Rephrasing Language Model](https://mlsanity.com/paper/2308.08796/) (2023)
- [Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning](https://mlsanity.com/paper/2505.14216/) (2025)
- [CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers](https://mlsanity.com/paper/2211.08788/) (2022)
- [Does Bigger Mean Better? Comparitive Analysis of CNNs and Biomedical Vision Language Modles in Medical Diagnosis](https://mlsanity.com/paper/2510.00411/) (2025)
- [Rainbow Noise: Stress-Testing Multimodal Harmful-Meme Detectors on LGBTQ Content](https://mlsanity.com/paper/2507.19551/) (2025)

## Built on by (most cited first, 10 of 10)

- [EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis](https://mlsanity.com/paper/2602.02551/) (2026)
- [One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement](https://mlsanity.com/paper/2604.25444/) (2026)
- [CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning](https://mlsanity.com/paper/2603.28135/) (2026)
- [Time-TK: A Multi-Offset Temporal Interaction Framework Combining Transformer and Kolmogorov-Arnold Networks for Time Series Forecasting](https://mlsanity.com/paper/2602.11190/) (2026)
- [Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendation](https://mlsanity.com/paper/2603.11503/) (2026)
- [Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems](https://mlsanity.com/paper/2603.12752/) (2026)
- [From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning](https://mlsanity.com/paper/2608.21897/) (2026)
- [AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting](https://mlsanity.com/paper/2609.16573/) (2026)
- [CoRe: Coherence and Relational Alignment for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2609.19670/) (2026)
- [VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction](https://mlsanity.com/paper/2609.36804/) (2026)

## Abstract (arXiv)

Large-scale Chinese spelling correction (CSC) remains critical for real-world text processing, yet existing LLMs and supervised methods lack robustness to novel errors and rely on costly annotations. We introduce CEC-Zero, a zero-supervision reinforcement learning framework that addresses this by enabling LLMs to correct their own mistakes. CEC-Zero synthesizes errorful inputs from clean text, computes cluster-consensus rewards via semantic similarity and candidate agreement, and optimizes the policy with PPO. It outperforms supervised baselines by 10--13 F1 points and strong LLM fine-tunes by 5--8 points across 9 benchmarks, with theoretical guarantees of unbiased rewards and convergence. CEC-Zero establishes a label-free paradigm for robust, scalable CSC, unlocking LLM potential in noisy text pipelines.