Giovanni Puccetti from ISTI-CNR presented research on linguistic probing of language models like BERT and RoBERTa. The research investigates the ability of these models to encode linguistic properties, linking this ability to outlier parameters. Preliminary work on fine-tuning LLMs in Italian and detecting synthetic news generation was also presented. Why it matters: Understanding the inner workings and linguistic capabilities of LLMs is crucial for improving their reliability and adapting them to diverse languages like Arabic.
This paper introduces a predictive analysis of Arabic court decisions, utilizing 10,813 real commercial court cases. The study evaluates LLaMA-7b, JAIS-13b, and GPT3.5-turbo models under zero-shot, one-shot, and fine-tuned training paradigms, also experimenting with summarization and translation. GPT-3.5 models significantly outperformed others, exceeding JAIS model performance by 50%, while also demonstrating the unreliability of most automated metrics. Why it matters: This research bridges computational linguistics and Arabic legal analytics, offering insights for enhancing judicial processes and legal strategies in the Arabic-speaking world.
The paper introduces a benchmark of 1,000 multiple-choice questions to evaluate LLMs on Islamic inheritance law ('ilm al-mawarith). Seven LLMs were tested, with o3 and Gemini 2.5 achieving over 90% accuracy, while ALLaM, Fanar, LLaMA, and Mistral scored below 50%. Error analysis revealed limitations in handling structured legal reasoning. Why it matters: This research highlights the challenges and opportunities for adapting LLMs to complex, culturally-specific legal domains like Islamic jurisprudence.
The paper introduces ALLaM, a series of large language models for Arabic and English, designed to support Arabic Language Technologies. The models are trained with language alignment and knowledge transfer in mind, using a decoder-only architecture. ALLaM achieves state-of-the-art results on Arabic benchmarks like MMLU Arabic and Arabic Exams. Why it matters: This work advances Arabic NLP by providing high-performing LLMs and demonstrating effective techniques for cross-lingual transfer learning and alignment with human preferences.
This paper presents a UI-level evaluation of ALLaM-34B, an Arabic-centric LLM developed by SDAIA and deployed in the HUMAIN Chat service. The evaluation used a prompt pack spanning various Arabic dialects, code-switching, reasoning, and safety, with outputs scored by frontier LLM judges. Results indicate strong performance in generation, code-switching, MSA handling, reasoning, and improved dialect fidelity, positioning ALLaM-34B as a robust Arabic LLM suitable for real-world use.
This study reviews the use of large language models (LLMs) for Arabic language processing, focusing on pre-trained models and their applications. It highlights the challenges in Arabic NLP due to the language's complexity and the relative scarcity of resources. The review also discusses how techniques like fine-tuning and prompt engineering enhance model performance on Arabic benchmarks. Why it matters: This overview helps consolidate research directions and benchmarks in Arabic NLP, guiding future development of LLMs tailored for the Arabic language and its diverse dialects.
This article surveys the landscape of Arabic Large Language Models (ALLMs), tracing their evolution from early text processing systems to sophisticated AI models. It highlights the unique challenges and opportunities in developing ALLMs for the 422 million Arabic speakers across 27 countries. The paper also examines the evaluation of ALLMs through benchmarks and public leaderboards. Why it matters: ALLMs can bridge technological gaps and empower Arabic-speaking communities by catering to their specific linguistic and cultural needs.