Pith. sign in

Theoretically, using manual annotation is a perfect solution, but it is too idealized and costly

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

REJECT 1

representative citing papers

CEC-Zero: Chinese Error Correction Solution Based on LLM

cs.CL · 2025-05-14 · reject · novelty 4.0

The authors claim that reinforcement learning with an embedding-clustering reward improves Chinese spelling correction and cross-domain generalization, but the evidence is missing key baselines and reproducibility artifacts.

citing papers explorer

Showing 1 of 1 citing paper.

  • CEC-Zero: Chinese Error Correction Solution Based on LLM cs.CL · 2025-05-14 · reject · none · ref 2

    The authors claim that reinforcement learning with an embedding-clustering reward improves Chinese spelling correction and cross-domain generalization, but the evidence is missing key baselines and reproducibility artifacts.