ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs
Changchun Liu, Kai Zhang, Junzhe Jiang, Zirui Liu, Hanqing Tao, Min Gao, Enhong Chen
Abstract
Chinese Spelling Check (CSC) aims to identify and correct spelling errors in Chinese texts, where enhanced semantic understanding of a sentence can significantly improve correction accuracy. Recently, Large Language Models (LLMs) have demonstrated exceptional mastery of world knowledge and semantic understanding, rendering them more robust against spelling errors. However, the application of LLMs in CSC is a double-edged sword, as they tend to unnecessarily alter sentence length and modify rare but correctly used phrases. In this paper, by leveraging the capabilities of LLMs while mitigating their limitations, we propose a novel plug-and-play Alignment-and-Replacement Module ARM that enhances the performance of existing CSC models and without the need for retraining or fine-tuning. Experiment results and analysis on three benchmark datasets demonstrate the effectiveness and competitiveness of the proposed module.
BibTeX
@inproceedings{liu-etal-2024-arm,
title = "{ARM}: An Alignment-and-Replacement Module for {C}hinese Spelling Check Based on {LLM}s",
author = "Liu, Changchun and
Zhang, Kai and
Jiang, Junzhe and
Liu, Zirui and
Tao, Hanqing and
Gao, Min and
Chen, Enhong",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.567/",
doi = "10.18653/v1/2024.emnlp-main.567",
pages = "10156--10168"
}