CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards
Zhiming Lin, Kai Zhao, Sophie Zhang, Peilai Yu, Canran Xiao
Abstract
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 zerosupervision 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.
BibTeX
@inproceedings{aaai2026_ceczerozerosuper,
title = {CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards},
author = {Zhiming Lin and Kai Zhao and Sophie Zhang and Peilai Yu and Canran Xiao},
booktitle = {AAAI 2026},
year = {2026}
}