Mohamed Alkaoud

Dr. Mohamed Alkaoud


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 February 2024 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
MAMohamed Alkaoud
Mohamed Alkaoud
This work introduces a new benchmark for the bilingual evaluation of large language models (LLMs) in English and Arabic. While LLMs have transformed various fields, their evaluation in Arabic remains limited. This work addresses this gap by proposing a novel evaluation method for LLMs in both Arabic and English, allowing for a direct comparison between the performance of the two languages. We build a new evaluation dataset based on the General Aptitude Test (GAT), a standardized test widely used for university admissions in the Arab world, that we utilize to measure the linguistic capabilities of LLMs. We conduct several experiments to examine the linguistic capabilities of ChatGPT and quantify how much better it is at English than Arabic. We also examine the effect of changing task descriptions from Arabic to English and vice-versa. In addition to that, we find that fastText can surpass ChatGPT in finding Arabic word analogies. We conclude by showing that GPT-4 Arabic linguistic capabilities are much better than ChatGPT’s Arabic capabilities and are close to ChatGPT’s English capabilities.

14 January 2025 in IEEE Access
Verified
Journal Article
Open access
MAMohamed Alkaoud
Mohamed Alkaoud
This paper addresses the challenge of efficient semantic question similarity in Arabic by leveraging fastText embeddings and a simple neural network architecture. Our model (FArSS) avoids the complexities of recurrent connections and attention mechanisms, resulting in a streamlined and efficient approach. With strategic data augmentation, our model achieves an F1-score of 0.928, closely competing with state-of-the-art models that rely on advanced architectures employing self-attention mechanisms. Additionally, our model outperforms both GPT-4o and GPT-4 in semantic question similarity in Arabic, underscoring the potential of specialized, efficient models to surpass large language models in specific tasks. This work demonstrates that our method not only maintains high performance but also ensures fast training and inference times. The practical advantages of our approach make it especially suitable for real-time applications, contributing to the development of more effective and efficient natural language processing systems. Our findings highlight the continued importance of efficient tailored models in addressing specific natural language processing challenges.

8 October 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
MAMohamed Alkaoud
Mohamed Alkaoud
This paper presents an investigation into fine-tuning large language models (LLMs) for Arabic natural language processing (NLP) tasks. Although recent multilingual LLMs have made remarkable progress in zero-shot and few-shot settings, specialized models such as fine-tuned BERT variants continue to define state-of-the-art (SOTA) performance in many Arabic tasks. We demonstrate that by fine-tuning a general-purpose LLM (GPT-4o mini) on only a small subset (3.0%–7.5%) of the training samples, we exceed previous best reported results in sentiment analysis (ArSAS) and sarcasm detection (ArSarcasm), while achieving performance statistically comparable to the SOTA in news categorization (ASND). This study highlights that LLMs, when properly adapted, can outperform established models without relying on full-scale annotated training sets. Furthermore, our analysis with the open-source Gemma-3-27B model confirms the generalizability of our data-efficient method. Notably, this approach enabled the model to achieve performance statistically comparable to SOTA on all three tasks, although the proprietary GPT-4o mini maintained an overall performance advantage. We further compare GPT-4o with GPT-4o mini to examine the impact of model size on fine-tuning. GPT-4o outperforms GPT-4o mini across all sample sizes but by small margins (<1%). Notably, GPT-4o fine-tuned on 100 samples achieves marginally better performance than GPT-4o mini fine-tuned on 500 samples, indicating that larger models require fewer labeled examples. Additionally, we find that fine-tuning performance follows predictable scaling, with GPT-4o mini’s performance growth function accurately estimating GPT-4o’s results (error < 0.005). This enables efficient performance estimation for larger models using smaller ones. Our findings emphasize the practical benefits of fine-tuning LLMs for Arabic NLP, while demonstrating predictable scaling laws that can guide efficient model selection and adaptation.

29 February 2024
Verified
Open access
MAMohamed Alkaoud
Mohamed Alkaoud
This work introduces a new benchmark for the bilingual evaluation of large language models (LLMs) in English and Arabic. While LLMs have transformed various fields, their evaluation in Arabic remains limited. This work addresses this gap by proposing a novel evaluation method for LLMs in both Arabic and English, allowing for a direct comparison between the performance of the two languages. We build a new evaluation dataset based on the General Aptitude Test (GAT), a standardized test widely used for university admissions in the Arab world, that we utilize to measure the linguistic capabilities of LLMs. We conduct several experiments to examine the linguistic capabilities of ChatGPT and quantify how much better it is at English than Arabic. We also examine the effect of changing task descriptions from Arabic to English and vice-versa. In addition to that, we find that fastText can surpass ChatGPT in finding Arabic word analogies. We conclude by showing that GPT-4 Arabic linguistic capabilities are much better than ChatGPT’s Arabic capabilities and are close to ChatGPT’s English capabilities.

1 January 2026 in IEEE Access
Verified
Journal Article
Open access
IJIbrahim Mohd Jamadi
Ibrahim Mohd Jamadi
SASyahid Anuar
Syahid Anuar
SISaad M. Ijad
Saad M. Ijad
MAMohamed Alkaoud
Mohamed Alkaoud

29 February 2024
Verified
Open access
MAMohamed Alkaoud
Mohamed Alkaoud
This work introduces a new benchmark for the bilingual evaluation of large language models (LLMs) in English and Arabic. While LLMs have transformed various fields, their evaluation in Arabic remains limited. This work addresses this gap by proposing a novel evaluation method for LLMs in both Arabic and English, allowing for a direct comparison between the performance of the two languages. We build a new evaluation dataset based on the General Aptitude Test (GAT), a standardized test widely used for university admissions in the Arab world, that we utilize to measure the linguistic capabilities of LLMs. We conduct several experiments to examine the linguistic capabilities of ChatGPT and quantify how much better it is at English than Arabic. We also examine the effect of changing task descriptions from Arabic to English and vice-versa. In addition to that, we find that fastText can surpass ChatGPT in finding Arabic word analogies. We conclude by showing that GPT-4 Arabic linguistic capabilities are much better than ChatGPT’s Arabic capabilities and are close to ChatGPT’s English capabilities.