To Err Is Human, but Llamas Can Learn It Too
arxiv(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要