不训练模型，用大模型自动纠正中文错字、漏字、多字。
A Training-free LLM-based Approach to General Chinese Character Error Correction
- 基于编辑距离和提示工程，无需训练即可处理三类汉字错误。
- 140亿参数模型性能媲美50倍大的传统模型。
- 适用于无标注数据场景，适合快速部署纠错系统。
中文拼写纠错（CSC）旨在修正中文文本中的字符错误。传统CSC主要关注因误打导致的字符替换错误，而漏字和多字这两种常见错误在标注和评估中常被忽略，限制了任务的实际应用。为此，我们提出通用中文字符纠错（C2EC）任务，涵盖三类错误。通过整合并人工验证CCTC与Lemon数据集，构建高质量的C2EC基准。将无需训练的提示无关方法扩展至C2EC，利用莱文斯坦距离处理长度变化，并引入额外提示式大语言模型（LLM）提升性能。实验表明，该方法使一个140亿参数的LLM在常规CSC和C2EC任务上达到接近50倍规模模型的水平，且无需任何微调。
原文摘要 · Abstract (English)
Chinese spelling correction (CSC) is a crucial task that aims to correct character errors in Chinese text. While conventional CSC focuses on character substitution errors caused by mistyping, two other common types of character errors, missing and redundant characters, have received less attention. These errors are often excluded from CSC datasets during the annotation process or ignored during evaluation, even when they have been annotated. This issue limits the practicality of the CSC task. To address this issue, we introduce the task of General Chinese Character Error Correction (C2EC), which focuses on all three types of character errors. We construct a high-quality C2EC benchmark by combining and manually verifying data from CCTC and Lemon datasets. We extend the training-free prompt-free CSC method to C2EC by using Levenshtein distance for handling length changes and leveraging an additional prompt-based large language model (LLM) to improve performance. Experiments show that our method enables a 14B-parameter LLM to be on par with models nearly 50 times larger on both conventional CSC and C2EC tasks, without any fine-tuning.
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。