Metraipolis › archive › dc_7034a3df4239

Precision--Recall Trade-off on the Inference Level for LLMs in Grammatical Error Correction — arXiv:2610.41698

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41698
License (as archived)
CC0-1.0
Archived
2026-11-03T07:55:12.945Z
SHA-256 of the archived text
1e4ab788f744d6f5f67ce7b24fdb2bd81e56d2bbddf853b419e130f9b22b4d3c
Stable URL of this page
https://metraipolis.com/documento/dc_7034a3df4239

How to cite

Precision--Recall Trade-off on the Inference Level for LLMs in Grammatical Error Correction — arXiv:2610.41698 — arXiv (en), https://arxiv.org/abs/2610.41698 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7034a3df4239 (Metraipolis archive dc_7034a3df4239, sha256 1e4ab788f744d6f5f67ce7b24fdb2bd81e56d2bbddf853b419e130f9b22b4d3c)
BibTeX
@misc{dc7034a3df4239,
  title = {Precision--Recall Trade-off on the Inference Level for LLMs in Grammatical Error Correction — arXiv:2610.41698},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41698},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7034a3df4239; sha256 1e4ab788f744d6f5f67ce7b24fdb2bd81e56d2bbddf853b419e130f9b22b4d3c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41698. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have recently been adopted for Grammatical Error Correction (GEC), achieving strong performance via both full fine-tuning and prompt-based approaches. As probabilistic sequence models, LLMs expose inference-time parameters that directly modify token generation behavior; however, their potential for controlling GEC-specific trade-offs has not been systematically studied. In this work, we investigate decoding strategies for grammatical error correction. We show that the repetition penalty parameter enables controllable adjustment of the precision--recall trade-off at inference time, without modifying the model architecture, training procedure, or prompt. Through experiments on standard GEC benchmarks, we demonstrate that repetition-penalty-based decoding enables inference-time control of the precision--recall balance, conceptually related to methods previously proposed for sequence-to-sequence GEC models, such as Align-and-Predict Decoding (APD), while remaining simple and broadly applicable to existing LLMs that expose inference-time decoding penalties.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41698 — 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 2026-11-03T07:49:46.004Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).