Researchers address the challenge of limited Arabic medical dialogue data by generating 80,000 synthetic question-answer pairs using ChatGPT-4o and Gemini 2.5 Pro, expanding an initial dataset of 20,000 records. They fine-tuned five LLMs, including Mistral-7B and AraGPT2, and evaluated performance using BERTScore and expert review. Results showed that training with ChatGPT-4o-generated data led to higher F1-scores and fewer hallucinations across models. Why it matters: This demonstrates the potential of synthetic data augmentation to improve domain-specific Arabic language models, particularly for low-resource medical NLP applications.
This paper analyzes Arabic text generated by LLMs like ALLaM, Jais, Llama, and GPT-4 across academic and social media domains using stylometric analysis. The study found detectable linguistic patterns that differentiate human-written from machine-generated Arabic text. BERT-based detection models achieved up to 99.9% F1-score in formal contexts, though cross-domain generalization remains a challenge. Why it matters: The research lays groundwork for detecting AI-generated misinformation in Arabic, a crucial step for preserving information integrity in Arabic-language contexts.
The paper introduces MedPromptX, a clinical decision support system using multimodal large language models (MLLMs), few-shot prompting (FP), and visual grounding (VG) for chest X-ray diagnosis, integrating imagery with EHR data. MedPromptX refines few-shot data dynamically for real-time adjustment to new patient scenarios and narrows the search area in X-ray images. The study introduces MedPromptX-VQA, a new visual question answering dataset, and demonstrates state-of-the-art performance with an 11% improvement in F1-score compared to baselines.
This paper introduces Pulmonary Embolism Detection using Contrastive Learning (PECon), a supervised contrastive pretraining strategy using both CT scans and EHR data to improve feature alignment between modalities for better PE diagnosis. PECon pulls sample features of the same class together while pushing away features of other classes. The approach achieves state-of-the-art results on the RadFusion dataset, with an F1-score of 0.913 and AUROC of 0.943.
This study explores fine-tuning large language models (LLMs) for Arabic medical text generation to improve hospital management systems. A unique dataset was collected from social media, capturing medical conversations between patients and doctors, and used to fine-tune models like Mistral-7B, LLaMA-2-7B, and GPT-2. The fine-tuned Mistral-7B model outperformed the others with a BERT F1-score of 68.5%. Why it matters: The research demonstrates the potential of generative AI to provide scalable and culturally relevant solutions for healthcare challenges in Arabic-speaking regions.
This paper explores multilingual satire detection methods in English and Arabic using zero-shot and chain-of-thought (CoT) prompting. It compares the performance of Jais-chat(13B) and LLaMA-2-chat(7B) on distinguishing satire from truthful news. Results show that CoT prompting significantly improves Jais-chat's performance, achieving an F1-score of 80% in English. Why it matters: This demonstrates the potential of Arabic LLMs like Jais to handle nuanced language tasks such as satire detection, which is critical for combating misinformation in the region.
This paper explores the use of deep learning for anomaly detection in sports facilities, with the goal of optimizing energy management. The researchers propose a method using Deep Feedforward Neural Networks (DFNN) and threshold estimation techniques to identify anomalies and reduce false alarms. They tested their approach on an aquatic center dataset at Qatar University, achieving 94.33% accuracy and 92.92% F1-score. Why it matters: The research demonstrates the potential of AI to improve energy efficiency and operational effectiveness in sports facilities within the GCC region.
This paper introduces two shared tasks for abusive and threatening language detection in Urdu, a low-resource language with over 170 million speakers. The tasks involve binary classification of Urdu tweets into Abusive/Non-Abusive and Threatening/Non-Threatening categories, respectively. Datasets of 2400/6000 training tweets and 1100/3950 testing tweets were created and manually annotated, along with logistic regression and BERT-based baselines. 21 teams participated and the best systems achieved F1-scores of 0.880 and 0.545 on the abusive and threatening language tasks, respectively, with m-BERT showing the best performance.