Technology Innovation Institute (TII) in the UAE has launched Falcon 180B, an open access large language model with 180 billion parameters trained on 3.5 trillion tokens. Falcon 180B ranks first on the Hugging Face Leaderboard for pretrained LLMs, outperforming Meta's LLaMA 2 and nearing the performance of OpenAI's GPT-4 and Google's PaLM 2. The model is available for research and commercial use under the 'Falcon 180B TII License', based upon Apache 2.0. Why it matters: This release strengthens the UAE's position in AI development and promotes open access to advanced AI technology, fostering innovation and collaboration.
KAUST has unveiled Shaheen III, the most powerful supercomputer in the Middle East and 18th globally, built by HPE. The system uses 2,800 NVIDIA GH200 Grace Hopper Superchips, tripling the processing power of its predecessor. Shaheen III will support research in Arabic LLMs, climate modeling, remote sensing, automated chemistry, and AI-driven healthcare. Why it matters: This infrastructure investment strengthens Saudi Arabia's position in AI and computational research, enabling advances tailored to the region's needs and priorities.
G42, a global leader in artificial intelligence based in Abu Dhabi, partnered with creative innovation company R/GA to launch alpha.G42.ai, a generative interface designed to transform traditional websites into dynamic, conversational systems. This prototype redefines a brand's digital presence by employing an intelligent agent powered by integrated large language models (LLMs) to generate and curate personalized content for each visitor in real-time. The system processes various content types as knowledge, which it then synthesizes to produce dynamic, tailored outputs for users interacting via voice or text, moving beyond static content management. Why it matters: This initiative from a major UAE AI firm pioneers a novel approach to web interfaces, potentially influencing future digital interactions and content delivery globally.
Researchers introduce HalluTruthQA, a new fine-grained benchmark designed for hallucination detection, localization, and explanation in Arabic question answering. This benchmark comprises 2,400 expert-curated examples across Islamic knowledge, history, science, and geography, featuring character-level error spans, human explanations, and various hallucination types. The study evaluated four open-source Arabic LLMs (ALLaM-7B, Falcon-H1R-7B, Qwen3-32B, SILMA) across detection, localization, factual verification, and explanation tasks, revealing no single model outperforms others across all metrics. Why it matters: HalluTruthQA provides a critical tool for advancing the factual accuracy and reliability of Arabic LLMs by enabling more granular and comprehensive hallucination evaluation beyond response-level detection.
Researchers have introduced HalluTruthQA, a new fine-grained benchmark designed for hallucination detection, localization, and explanation in Arabic Question Answering. The benchmark comprises 2,400 expert-curated examples spanning four knowledge-intensive domains: Islamic knowledge, history, science, and geography, with detailed annotations including character-level erroneous spans and human-written explanations. Four open-source LLMs ( extsc{Allam}, extsc{Falcon-H1}, extsc{Qwen32}, and extsc{Silma}) were evaluated, demonstrating varied performance across detection, localization, factual verification, and explanation tasks. Why it matters: This benchmark offers a comprehensive tool for evaluating and enhancing the factual accuracy and trustworthiness of Arabic LLMs, promoting more sophisticated assessment beyond simple hallucination detection.
This study investigates methods to steer Arabic Large Language Models (LLMs) towards generating specific dialects, addressing the challenge of data scarcity for dialectal Arabic. Researchers identified sparse neuron populations encoding dialect-specific features and developed a vector-steering approach using dialect-specific activation directions. These inference-time methods allow for controlling dialectal output by amplifying or suppressing neuron activity or injecting specific vectors. Why it matters: This research offers a principled, interpretability-grounded framework to improve dialectal accuracy in Arabic LLMs without fine-tuning, crucial for enhancing their utility in the diverse Arabic-speaking world.
Researchers from MBZUAI have proposed the Cylindrical Representation Hypothesis (CRH) to explain the instability and unpredictability observed in large language model steering. CRH relaxes the orthogonality assumption of the existing Linear Representation Hypothesis, positing a cylindrical structure where a central axis captures concept differences and a surrounding normal plane controls steering sensitivity. The hypothesis suggests that the intrinsic uncertainty in identifying specific sensitive sectors within this normal plane accounts for why steering outcomes frequently fluctuate even with well-aligned directions. Why it matters: This research offers a more robust theoretical framework for understanding and potentially improving the control and reliability of large language models.
Researchers at MBZUAI have developed a new method for controllable poetry generation in Arabic and its dialects, moving beyond traditional analysis tasks for Arabic poetry within Large Language Models (LLMs). They introduce a large-scale, instruction-based dataset in Modern Standard Arabic (MSA) and various Arabic dialects, enabling LLMs to perform tasks like writing, revising, and continuing poems based on user criteria. Experiments show that fine-tuning LLMs on this dataset results in models capable of generating poetry aligned with user requirements, validated by automated metrics and human evaluation. Why it matters: This work represents a significant advancement in Arabic Natural Language Processing, offering tools for creative expression and cultural preservation while opening new avenues for user-guided content generation in culturally rich text forms.