用投票法解决大模型语法纠错过改问题，不需训练也能提效。
Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction
- 对单模型生成的多个纠错结果按编辑粒度投票，避免过纠正。
- 在9个语言的基准上优于贪心和MBR解码，多数情况提升显著。
- 对提示词不敏感，适合实际部署，无需修改模型或重新训练。
使用大语言模型进行语法错误修正常面临过纠正问题。为此，我们提出一种无需训练的推理方法，在不修改模型或额外训练的前提下，对单个模型生成的多个候选结果进行编辑级的多数投票。该方法在涵盖英语、捷克语、德语、乌克兰语、韩语、印地语和罗马尼亚语的九个基准测试中，多数情况下优于贪婪解码和最小束长（MBR）解码。此外，其纠错质量在不同指令提示下保持稳定。我们开源了两个仓库，支持GEC数据集加载与大模型推理。
原文摘要 · Abstract (English)
Grammatical error correction using large language models often suffers from the over-correction issue. To mitigate this, we propose a training-free inference method that performs edit-level majority voting over multiple candidates generated by a single model, without requiring model modifications or additional training. Across nine benchmarks covering English, Czech, German, Ukrainian, Korean, Hindi, and Romanian, the proposed method outperforms both greedy and MBR decoding in most cases. Moreover, it yields stable correction quality regardless of the instruction prompts used. We release two repository supporting GEC datasets loading and LLM inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。