Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting

K Feng, Z Tang, J Li, M Zhang - CCF International Conference on Natural …, 2023 - Springer
Recent studies have revealed that grammatical error correction methods in the sequence-to-
sequence paradigm are vulnerable to adversarial attacks. Large Language Models (LLMs) …

PROTECT: Parameter-Efficient Tuning for Few-Shot Robust Chinese Text Correction

X Feng, T Gu, L Chang, X Liu - IEEE/ACM Transactions on …, 2024 - ieeexplore.ieee.org
Non-normative texts and euphemisms are widely spread on the Internet, making it more
difficult to moderate the content. These phenomena result from misspelling errors or …

Learning from Mistakes: Self-correct Adversarial Training for Chinese Unnatural Text Correction

X Feng, T Gu, X Liu, L Chang - arxiv preprint arxiv:2412.17279, 2024 - arxiv.org
Unnatural text correction aims to automatically detect and correct spelling errors or
adversarial perturbation errors in sentences. Existing methods typically rely on fine-tuning or …

Tibyan Corpus: Balanced and Comprehensive Error Coverage Corpus Using ChatGPT for Arabic Grammatical Error Correction

A Alrehili, A Alhothali - arxiv preprint arxiv:2411.04588, 2024 - arxiv.org
Natural language processing (NLP) utilizes text data augmentation to overcome sample size
constraints. Increasing the sample size is a natural and widely used strategy for alleviating …

Evaluating Performance of LLaMA2 Large Language Model Enhanced by QLoRA Fine-Tuning for English Grammatical Error Correction

J An, Y Bai, J Li, J Hu, R Li, Y **ao, R Hua - International Conference on …, 2024 - Springer
Abstract Large Language Models (LLMs) have experienced significant advancements
across various contexts. However, their impact on vertical fields remains understudied and …