Islam and Data Science Roundup

In “A TEI-Based Approach to Premodern Islamic Texts” (Digital Orientalist), Adrien de Jarmy (University of Strasbourg) and Clarck Junior Membourou Moimecheme (Sorbonne Nouvelle University) discuss the BADR Project, which “examines the genesis, transmission, and sociopolitical uses of narratives about the Battle of Badr (2/624) from their earliest attestations to contemporary reinterpretations. It explores how these… CONTINUE READING

In “BALSAM: A Platform for Benchmarking Arabic Large Language Models” (ACL Anthology), Rawan Al-Matham (King Salman Global Academy For Arabic Language) and others “introduce BALSAM, a comprehensive, community-driven benchmark aimed at advancing Arabic LLM development and evaluation. It includes 78 NLP tasks from 14 broad categories, with 52K examples divided into 37K test and 15K… CONTINUE READING

In “Islamiclegalbench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions” (arXiv), Ezieddin Elmahjub (Qatar University) and others observe, “As millions of Muslims worldwide turn to LLMs like GPT, Claude, and DeepSeek for religious guidance, a critical question emerges: Can these AI systems reliably reason about Islamic law?… CONTINUE READING

In “Is Lying Only Sinful in Islam? Exploring Religious Bias in Multilingual Large Language Models Across Major Religions” (arXiv), Kazi Abrab Hossain (BRAC University) and others “introduce BRAND: Bilingual Religious Accountable Norm Dataset, which focuses on the four main religions of South Asia: Buddhism, Christianity, Hinduism, and Islam, containing over 2,400 entries, and we used… CONTINUE READING

In “IslamTrust: A Benchmark for LLMs Alignment with Islamic Values” (Muslims in Machine Learning), Abderraouf Lahmar (Eötvös Loránd University) and others observe that the “alignment of most Large Language Models (LLMs) to broad, often non-Islamic ethical principles creates a significant gap for users from specific cultural and religious backgrounds. LLMs used within Muslim communities for… CONTINUE READING

In “Rāzī’s Pen or Ibn Sīnā’s Voice? A Stylometric Investigation of the Risāla fī al-Sikanjabīn” (Journal of Digital Islamicate Research), Zahra Alamdar (Iran University of Medical Sciences) and Hamed Arezaei (Iran University of Medical Sciences Tehran) argue that “the precise attribution of historical texts remains a persistent challenge, especially for prolific Islamic Golden Age figures… CONTINUE READING

In “Digital Eschatology in Islamicate Traditions: a Comparative Study of Inter-Religious Prophecies” (Journal of Digital Islamicate Studies), Mohammed Qasim Khan (University of Malaya Wilayah Persekutuan) “explores the emerging phenomenon of digital eschatology within Islamicate traditions by examining how artificial intelligence and digital platforms influence inter-religious apocalyptic narratives. Situating the research within the broader context of… CONTINUE READING

In “Detecting Text Reuse in Historical Arabic Texts: Challenges and Strategies” (Journal of Digital Islamicate Research),Tynan Kelly (Prince Mohammad Bin Fahd University) “introduces alNaql, a new TRD software specifically designed for Arabic. By incorporating algorithms tailored to Arabic’s unique morphological and syntactic properties, alNaql identifies significantly more reuse instances than currently available tools. We compare… CONTINUE READING

In “Handwriting Style Analysis in Arabic Papyri, Parchments, and Papers: the Case of Abū Hurayra” (Journal of Digital Islamicate Research), Leonora Sonego (Ludwig-Maximilians-Universität München) “evaluates a combined palaeographic-computational method to identify scribes in historic documents, more precisely Arabic papyri, where automatic feature extraction is not possible. The challenge is to define features that a human… CONTINUE READING

In “Context-Aware Extraction of Quranic References: A Hybrid Language Model- and Rule-Based Approach” (Muslims in Machine Learning Workshop), Alireza Sahebi (Sharif University of Technology) and others observe that “large language models (LLMs) often generate hallucinated or inaccurate Quranic content, highlighting the importance of tools capable of verifying and correcting such outputs.” They present “a multi-layered… CONTINUE READING