The linguistic inclusivity of Large Language Models (LLMs) such as ChatGPT, Gemni, JAIS, and AceGPT has not been sufficiently explored, particularly in their handling of low-resource languages like Arabic compared to English. While these models have shown impressive performance across various tasks, their effectiveness in Arabic remains under-examined. Punctuation, critical for sentence structure and comprehension in tasks like speech analysis, synthesis, and machine translation, requires precise prediction. This paper assesses seven LLMs: GPT4-o, Gemni1.5, JAIS, AceGPT, SILMA, ALLaM, and CommandR+ for Arabic punctuation prediction. Additionally, the performance of fine-tuned AraBERT is compared with these models in zero-shot and few-shot settings using a proposed Arabic punctuation prediction corpus of 10,044 sentences. The experiments demonstrate that while AraBERT performs well for specific punctuation marks, LLMs show significant promise in zero-shot learning, with further improvements in few-shot scenarios. These findings highlight the potential of LLMs to enhance the automation and accuracy of Arabic text processing.

This paper investigates the effectiveness of retrieval-augmented generation (RAG) pipelines, focusing on the Arabic lexical information retrieval. Specifically, it analyzes how embedding models affect the recall of Arabic lexical information and evaluates the ability of large language models (LLMs) to produce accurate and contextually relevant answers within the RAG pipelines. We examine a dataset of over 88,000 words from the Riyadh dictionary and evaluate the models using metrics such as Top-K Recall, Mean Reciprocal Rank (MRR), F1 Score, Cosine Similarity, and Accuracy. The research assesses the capabilities of several embedding models, including E5-large, BGE, AraBERT, CAMeLBERT, and AraELECTRA, highlighting a disparity in performance between sentence embeddings and word embeddings. Sentence embedding with E5 achieved the best results, with a Top-5 Recall of 0.88, and an MRR of 0.48. For the generation models, we evaluated GPT-4, GPT-3.5, SILMA-9B, Gemini-1.5, Aya-8B, and AceGPT-13B based on their ability to generate accurate and contextually appropriate responses. GPT-4 demonstrated the best performance, achieving an F1 score of 0.90, an accuracy of 0.82, and a cosine similarity of 0.87. Our results emphasize the strengths and limitations of both embedding and generation models in Arabic tasks.