Islam and Data Science Roundup

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

In “A Rule-Based System for Identifying Islamic Citation in LLM Outputs” (IslamicEval 2025), Fatimah Emad Eldin (Cairo University) “presents the Isnad AI system…which focuses on identifying character-level spans of Quranic verses (Ayahs) and Prophetic sayings (Hadiths) within Large Language Model (LLM) outputs….The primary contribution is a novel rule-based data preprocessing and augmentation pipeline, through which… CONTINUE READING

In “LLM Agent-Based Modeling for Zakat Policy: Simulation in Islamic Finance” (Muslims in Machine Learning Workshop), Zaur Omarov (Lomonosov Moscow State University) and others introduce “a novel approach to simulating Zakat policy by leveraging Large Language Model (LLM) enhanced Agent-Based Modeling (ABM)…and propose a multi-agent system where LLM-powered agents represent diverse economic actors within an… CONTINUE READING

In “QURAN-MD: A Fine-Grained Multilingual Multimodal Dataset of the Quran” (Muslims in Machine Learning Workshop), Muhammad Umar Salman (Mohamed bin Zayed University of Artificial Intelligence) and others “present QURAN-MD, a comprehensive multimodal dataset of the Quran that integrates textual, linguistic, and audio dimensions at the verse and word levels.For each verse (ayah), the dataset provides… CONTINUE READING

In “Linear to Table, Table to Linear” (KITAB Project Blog), Lorenz Nigst (Aga Khan University) uses the KITAB Project’s diff viewer to examine text reuse across two manuscripts “containing a short narrative involving Muḥammad Khawārazmshāh…[on] dream interpretation.” In “Lemmatization as a Classification Task: Results from Arabic across Multiple Genres” (arXiv), Mostafa Saeed (New York University… CONTINUE READING