GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP
This work addresses the gap in understanding ChatGPT's efficacy for Arabic languages and dialects, providing insights for researchers and practitioners in multilingual NLP, though it is incremental as it extends existing evaluation frameworks to a new linguistic context.
The study evaluated ChatGPT's performance on Arabic NLP tasks, finding that it was consistently outperformed by smaller models fine-tuned on Arabic, with GPT-4 also showing shortcomings in handling dialects compared to Modern Standard Arabic.
ChatGPT's emergence heralds a transformative phase in NLP, particularly demonstrated through its excellent performance on many English benchmarks. However, the model's efficacy across diverse linguistic contexts remains largely uncharted territory. This work aims to bridge this knowledge gap, with a primary focus on assessing ChatGPT's capabilities on Arabic languages and dialectal varieties. Our comprehensive study conducts a large-scale automated and human evaluation of ChatGPT, encompassing 44 distinct language understanding and generation tasks on over 60 different datasets. To our knowledge, this marks the first extensive performance analysis of ChatGPT's deployment in Arabic NLP. Our findings indicate that, despite its remarkable performance in English, ChatGPT is consistently surpassed by smaller models that have undergone finetuning on Arabic. We further undertake a meticulous comparison of ChatGPT and GPT-4's Modern Standard Arabic (MSA) and Dialectal Arabic (DA), unveiling the relative shortcomings of both models in handling Arabic dialects compared to MSA. Although we further explore and confirm the utility of employing GPT-4 as a potential alternative for human evaluation, our work adds to a growing body of research underscoring the limitations of ChatGPT.