← Search

Zhiming Lin

2 accepted papers

2026

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

AAAI 2026technical

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 ena

Cited by 0SourcePDFScholar
2026

From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samples

AAAI 2026technical

How should we quantify the value of each training example when datasets are large, heterogeneous, and geometrically structured? Classical Data-Shapley answers in principle, but its O(n!) complexity and point-wise perspective are ill-suited to modern scales. We propose Hierarchical Contrastive Data V

Cited by 0SourcePDFScholar