4 citations · 6 across the 18 of their papers we have counts for
11 papers · 1 filter
UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat
Omer Nacar
Large language models (LLMs) trained primarily on English corpora often struggle to capture the linguistic and cultural nuances of Arabic. To address this gap, the Saudi Data and A…
SHAMI-MT: A Syrian Arabic Dialect to Modern Standard Arabic Bidirectional Machine Translation System
Serry Sibaee, Omer Nacar, Yasser Al-Habashi +2
The rich linguistic landscape of the Arab world is characterized by a significant gap between Modern Standard Arabic (MSA), the language of formal communication, and the diverse re…
QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation
Ahmed Wasfy, Omer Nacar, Abdelakreem Elkhateb +4
The inherent complexities of Arabic script; its cursive nature, diacritical marks (tashkeel), and varied typography, pose persistent challenges for Optical Character Recognition (O…
From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation
Serry Sibaee, Omer Nacar, Adel Ammar +3
This paper addresses critical gaps in Arabic language model evaluation by establishing comprehensive theoretical guidelines and introducing a novel evaluation framework. We first a…
SARD: A Large-Scale Synthetic Arabic OCR Dataset for Book-Style Text Recognition
Omer Nacar, Yasser Al-Habashi, Serry Sibaee +2
Arabic Optical Character Recognition (OCR) is essential for converting vast amounts of Arabic print media into digital formats. However, training modern OCR models, especially powe…
GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training
Omer Nacar, Anis Koubaa, Serry Sibaee +3
Semantic textual similarity (STS) is a critical task in natural language processing (NLP), enabling applications in retrieval, clustering, and understanding semantic relationships…
Optimizing Retrieval-Augmented Generation: Analysis of Hyperparameter Impact on Performance and Efficiency
Adel Ammar, Anis Koubaa, Omer Nacar +1
Large language models achieve high task performance yet often hallucinate or rely on outdated knowledge. Retrieval-augmented generation (RAG) addresses these gaps by coupling gener…
Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset
Fakhraddin Alwajih, Samar M. Magdy, Abdellah El Mekki +34
Mainstream large vision-language models (LVLMs) inherently encode cultural biases, highlighting the need for diverse multimodal datasets. To address this gap, we introduce PEARL, a…
NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communities
Abdellah El Mekki, Houdaifa Atou, Omer Nacar +2
Enhancing the linguistic capabilities of Large Language Models (LLMs) to include low-resource languages is a critical research area. Current research directions predominantly rely…
Advancing Arabic Reverse Dictionary Systems: A Transformer-Based Approach with Dataset Construction Guidelines
Serry Sibaee, Samar Ahmed, Abdullah Al Harbi +4
This study addresses the critical gap in Arabic natural language processing by developing an effective Arabic Reverse Dictionary (RD) system that enables users to find words based…
Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs
Fakhraddin Alwajih, Abdellah El Mekki, Samar Mohamed Magdy +41
As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce our dataset, a year-l…