RAIR：用于中文拼写纠错的检索增强迭代优化
RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction
AI总结：
针对LLMs在专业领域中文拼写纠错及变长场景的不足，提出RAIR框架，通过自适应构建检索语料库与微调检索器捕捉纠错模式，有效提升了领域纠错与变长纠错性能。
摘要：
中文拼写纠错（CSC）旨在检测并纠正句子中的错误标记。传统CSC侧重于等长纠错并使用预训练语言模型（PLMs）。尽管大型语言模型（LLMs）在识别和纠正潜在错误方面展现出显著成功，但它们通常难以适应特定领域的纠错，尤其是在遇到专业领域的术语时。为了解决领域适应问题，我们提出了一种检索增强迭代优化（RAIR）框架。该方法从特定领域的训练数据和词典中自适应地构建检索语料库，并采用微调的检索器以确保其能够捕捉纠错模式。我们还将等长纠错扩展到了变长纠错场景。大量实验表明，我们的框架在领域拼写纠错上优于现有方法，并显著提升了LLMs在变长场景下的性能。
英文摘要：
Chinese Spelling Correction (CSC) aims to detect and correct erroneous tokens in sentences. Traditional CSC focuses on equal length correction and uses pretrained language models (PLMs). While Large Language Models (LLMs) have shown remarkable success in identifying and rectifying potential errors, they often struggle with adapting to domain-specific corrections, especially when encountering terminologies in specialized domains. To address domain adaptation, we propose a \textbf{R}etrieval-\textbf{A}ugmented \textbf{I}terative \textbf{R}efinement (RAIR) framework. Our approach constructs a retrieval corpus adaptively from domain-specific training data and dictionaries, employing a fine-tuned retriever to ensure that the retriever catches the error correction pattern. We also extend equal-length into variable-length correction scenarios. Extensive experiments demonstrate that our framework outperforms current approaches in domain spelling correction and significantly improves the performance of LLMs in variable-length scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
