Metraipolis › archive › dc_31b059dcbbe1

VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction — arXiv:2609.36804

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36804
License (as archived)
CC0-1.0
Archived
2026-10-07T16:26:22.775Z
SHA-256 of the archived text
80ddd3167f4fcb1d8aece2001390abe17c8e4d0172387c6d279c49480b9451a0
Stable URL of this page
https://metraipolis.com/documento/dc_31b059dcbbe1

How to cite

VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction — arXiv:2609.36804 — arXiv (en), https://arxiv.org/abs/2609.36804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31b059dcbbe1 (Metraipolis archive dc_31b059dcbbe1, sha256 80ddd3167f4fcb1d8aece2001390abe17c8e4d0172387c6d279c49480b9451a0)
BibTeX
@misc{dc31b059dcbbe1,
  title = {VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction — arXiv:2609.36804},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36804},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31b059dcbbe1; sha256 80ddd3167f4fcb1d8aece2001390abe17c8e4d0172387c6d279c49480b9451a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Chinese Semantic Error Correction (CSEC) targets semantic errors in Chinese text, which are typically more subtle and complex than spelling and grammatical errors but remain relatively underexplored. Existing LLM-based approaches face two recurring obstacles in this task: over-correction, and unclear interaction between Chain-of-Thought (CoT) reasoning and self-consistency decoding, such that the benefits brought by CoT cannot be reliably transferred to final corrections. We propose Vote-guided Advantage Allocation for CSEC (VAA-CSEC), a multi-stage framework that combines CoT distillation, Supervised Fine-Tuning (SFT), Reinforcement Learning (RL) and self-consistency decoding. During RL, we design a task-specific reward function that directly aligned with the minimal-editing principle of CSEC. We further introduce Group-Level Relative Policy Optimization (GLPO), which reallocates GRPO advantages according to the margin between individual rollout rewards and the vote-aggregated group reward, aligning the RL training objective with the self-consistency objective used at inference time. Experiments on CSED-C and NaSGEC-Exam show that VAA-CSEC outperforms all LLM-based baselines on CSED-C with an F0.5 of 47.72%, achieves the highest recall of 42.15% among all methods, and establishes a new state of the art of 41.55% F0.5 on NaSGEC-Exam.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.36804 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.891Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).