English

ChatGPT for Arabic Grammatical Error Correction

Artificial Intelligence 2023-08-10 v1

Abstract

Recently, large language models (LLMs) fine-tuned to follow human instruction have exhibited significant capabilities in various English NLP tasks. However, their performance in grammatical error correction (GEC) tasks, particularly in non-English languages, remains significantly unexplored. In this paper, we delve into abilities of instruction fine-tuned LLMs in Arabic GEC, a task made complex due to Arabic's rich morphology. Our findings suggest that various prompting methods, coupled with (in-context) few-shot learning, demonstrate considerable effectiveness, with GPT-4 achieving up to 65.4965.49 F\textsubscript{1} score under expert prompting (approximately 55 points higher than our established baseline). This highlights the potential of LLMs in low-resource settings, offering a viable approach for generating useful synthetic data for model training. Despite these positive results, we find that instruction fine-tuned models, regardless of their size, significantly underperform compared to fully fine-tuned models of significantly smaller sizes. This disparity highlights a substantial room for improvements for LLMs. Inspired by methods from low-resource machine translation, we also develop a method exploiting synthetic data that significantly outperforms previous models on two standard Arabic benchmarks. Our work sets new SoTA for Arabic GEC, with 72.19%72.19\% and 73.2673.26 F1_{1} on the 2014 and 2015 QALB datasets, respectively.

Keywords

Cite

@article{arxiv.2308.04492,
  title  = {ChatGPT for Arabic Grammatical Error Correction},
  author = {Sang Yun Kwon and Gagan Bhatia and El Moatez Billah Nagoud and Muhammad Abdul-Mageed},
  journal= {arXiv preprint arXiv:2308.04492},
  year   = {2023}
}
R2 v1 2026-06-28T11:51:12.089Z