Walaa Medhat

Multi-View Behavioral Probing for Political Bias in Arabic and Multilingual Transformers Before and After Domain Adaptation

A. Abdelhameed, Ensaf Hussein Mohamed, Walaa Medhat

Political bias in transformer-based language models poses a critical challenge for applications involving politically sensitive Arabic news, yet systematic evaluation remains limited. This paper presents a multi-view behavioral framework to detect political bias in four pre-trained transformer models: AraBERTv2, CAMeLBERT, mBERT, and …

Égypte (code pays fourni par la source)

Cognitively Aligned Assessment Item Generation with Open-Source LLMs: A Comprehensive Evaluation on LearningQ

Mahmoud Badry, Walaa Medhat, Shereen A. Taie, Asmaa Hashem Sweidan

Automated generation of high-quality educational assessment items is still difficult, especially when it comes to higher-order cognitive skills. Although Large Language Models (LLMs) show promise, their structural validity and cognitive alignment are limited. This study systematically evaluates fine-tuning open-source LLMs using an …

Égypte (code pays fourni par la source)

Building Trust in LLM-based Code Translation through Transcompiler-assisted Prompting

Amira T. Mahmoud, Nahla Elaraby, Hala Zayed ., Ahmed Hassan et autres

Soudan, Égypte (code pays fourni par la source)