This study explores enhancing grammatical error correction (GEC) through
artificial error generation (AEG) using language models (LMs). Specifically, we
fine-tune Llama 2-based LMs for error generation and find that this approach
yields synthetic errors akin to human errors. Next, we train GEC Llama models
with the help of these artificial errors and outperform previous
state-of-the-art error correction models, with gains ranging between 0.8 and 6
F0.5 points across all tested languages (German, Ukrainian, and Estonian).
Moreover, we demonstrate that generating errors by fine-tuning smaller
sequence-to-sequence models and prompting large commercial LMs (GPT-3.5 and
GPT-4) also results in synthetic errors beneficially affecting error generation
models.

该研究通过利用语言模型的人工错误生成（AEG）来增强语法错误校正（GEC），发现通过对基于 Llama 2 的语言模型进行微调，可以生成与人类错误相似的合成错误，进一步训练 GEC Llama 模型，使其在已测试的多种语言（德语、乌克兰语和爱沙尼亚语）中的校正效果超过了先前的最先进错误校正模型，并且证明了通过微调较小的序列到序列模型和提示大型商业语言模型（GPT-3.5 和 GPT-4）而生成的错误也对错误生成模型产生有益影响。