# RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction

arXiv: https://arxiv.org/abs/2504.18938 · HTML: https://mlsanity.com/paper/2504.18938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 26 Apr 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [Spelling Error Correction with Soft-Masked BERT](https://mlsanity.com/paper/2005.07421/) (2020)
- [ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information](https://mlsanity.com/paper/2106.16038/) (2021)
- [On the (In)Effectiveness of Large Language Models for Chinese Text Correction](https://mlsanity.com/paper/2307.09007/) (2023)
- [Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking](https://mlsanity.com/paper/2105.12306/) (2021)
- [RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering](https://mlsanity.com/paper/2407.13998/) (2024)
- [General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining](https://mlsanity.com/paper/2203.10929/) (2022)
- [Rethinking Masked Language Modeling for Chinese Spelling Correction](https://mlsanity.com/paper/2305.17721/) (2023)
- [Accurate and Nuanced Open-QA Evaluation Through Textual Entailment](https://mlsanity.com/paper/2405.16702/) (2024)
- [C-LLM: Learn to Check Chinese Spelling Errors Character by Character](https://mlsanity.com/paper/2406.16536/) (2024)
- [Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking](https://mlsanity.com/paper/2403.08492/) (2024)
- [Error-Robust Retrieval for Chinese Spelling Check](https://mlsanity.com/paper/2211.07843/) (2022)
- [Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning](https://mlsanity.com/paper/2411.17679/) (2024)
- [RSpell: Retrieval-augmented Framework for Domain Adaptive Chinese Spelling Check](https://mlsanity.com/paper/2308.08176/) (2023)
- [Learning from Mistakes: Self-correct Adversarial Training for Chinese Unnatural Text Correction](https://mlsanity.com/paper/2412.17279/) (2024)
- [Chinese Spelling Correction: A Comprehensive Survey of Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2502.11508/) (2025)
- [Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs](https://mlsanity.com/paper/2409.16005/) (2024)
- [PERL: Pinyin Enhanced Rephrasing Language Model for Chinese ASR N-best Error Correction](https://mlsanity.com/paper/2412.03230/) (2024)

## Abstract (arXiv)

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 Retrieval-Augmented Iterative Refinement (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.