A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models
Authors:
Preprint
Abstract
This work proposes a simple training-free prompt-free approach to leverage large language models (LLMs) for the Chinese spelling correction (CSC) task, which is totally different from all previous CSC approaches. The key idea is to use an LLM as a pure language model in a conventional manner. The LLM goes through the input sentence from the beginning, and at each inference step, produces a distribution over its vocabulary for deciding the next token, given a partial sentence. To ensure that the output sentence remains faithful to the input sentence, we design a minimal distortion model that utilizes pronunciation or shape similarities between the original and replaced characters. Furthermore, we propose two useful reward strategies to address practical challenges specific to the CSC task. Experiments on five public datasets demonstrate that our approach significantly improves LLM performance, enabling them to compete with state-of-the-art domain-general CSC models.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and AccelerationGetMobile: Mobile Computing and Communications, 2025
- Chinese Spelling Correction as Rephrasing Language ModelProceedings of the AAAI Conference on Artificial Intelligence, 2024
- SoftCorrect: Error Correction with Soft Detection for Automatic Speech RecognitionProceedings of the AAAI Conference on Artificial Intelligence, 2023
- General and Domain-adaptive Chinese Spelling Check with Error-consistent PretrainingACM Transactions on Asian and Low-Resource Language Information Processing, 2023
- Is Chinese Spelling Check ready? Understanding the correction behavior in real-world scenariosAI Open, 2023
- MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction2022
- Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking2021
- Chunk-based Chinese Spelling Check with Global Optimization2020
- Spelling Error Correction with Soft-Masked BERT2020
- AISHELL-1: An open-source Mandarin speech corpus and a speech recognition baseline2017