# ChatGPT for Arabic Grammatical Error Correction

arXiv: https://arxiv.org/abs/2308.04492 · HTML: https://mlsanity.com/paper/2308.04492/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 48 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [GECToR -- Grammatical Error Correction: Tag, Not Rewrite](https://mlsanity.com/paper/2005.12592/) (2020)
- [ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic](https://mlsanity.com/paper/2101.01785/) (2020)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [A Simple Recipe for Multilingual Grammatical Error Correction](https://mlsanity.com/paper/2106.03830/) (2021)
- [Encode, Tag, Realize: High-Precision Text Editing](https://mlsanity.com/paper/1909.01187/) (2019)
- [Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation](https://mlsanity.com/paper/2304.01746/) (2023)
- [Parallel Iterative Edit Models for Local Sequence Transduction](https://mlsanity.com/paper/1910.02893/) (2019)
- [Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation](https://mlsanity.com/paper/2305.15011/) (2023)
- [ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark](https://mlsanity.com/paper/2303.13648/) (2023)
- [AraT5: Text-to-Text Transformers for Arabic Language Generation](https://mlsanity.com/paper/2109.12068/) (2021)
- [Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task](https://mlsanity.com/paper/1804.05940/) (2018)
- [NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2010.11334/) (2020)
- [ORCA: A Challenging Benchmark for Arabic Language Understanding](https://mlsanity.com/paper/2212.10758/) (2022)
- [Grammatical Error Correction: A Survey of the State of the Art](https://mlsanity.com/paper/2211.05166/) (2022)
- [A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction](https://mlsanity.com/paper/1801.08831/) (2018)
- [AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization](https://mlsanity.com/paper/2203.10945/) (2022)
- [Automatic Error Type Annotation for Arabic](https://mlsanity.com/paper/2109.08068/) (2021)
- [Revisiting Grammatical Error Correction Evaluation and Beyond](https://mlsanity.com/paper/2211.01635/) (2022)
- [Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction](https://mlsanity.com/paper/2203.13064/) (2022)
- [Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models](https://mlsanity.com/paper/1809.01534/) (2018)

## Built on by (most cited first, 5 of 5)

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [Large Language Models and Arabic Content: A Review](https://mlsanity.com/paper/2505.08004/) (2025)
- [Tibyan Corpus: Balanced and Comprehensive Error Coverage Corpus Using ChatGPT for Arabic Grammatical Error Correction](https://mlsanity.com/paper/2411.04588/) (2024)
- [Towards the Development of Balanced Synthetic Data for Correcting Grammatical Errors in Arabic: An Approach Based on Error Tagging Model and Synthetic Data Generating Model](https://mlsanity.com/paper/2502.05312/) (2025)
- [ArbESC+: Arabic Enhanced Edit Selection System Combination for Grammatical Error Correction Resolving conflict and improving system combination in Arabic GEC](https://mlsanity.com/paper/2511.14230/) (2025)

## Abstract (arXiv)

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 65.49 Ftextsubscript1 score under expert prompting (approximately 5 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% and 73.26 F1 on the 2014 and 2015 QALB datasets, respectively.