arXiv AI By M Waleed Kadous, Amr Elsayed, Abdullah Al Nahas, Ashraf Haress

Ansari: A Retrieval-Grounded Islamic AI Assistant -- Architecture, Deployment, and Lessons from 140,000 Conversations

Read the original on arXiv AI →

Ansari is a retrieval‑grounded Islamic AI assistant that has handled over 140,000 conversations in more than 25 languages since June 2023. It uses an agentic retrieval loop where a language model searches authenticated Islamic corpora—including the Qur’an, hadith collections, fiqh encyclopedias, and tafsir sources—and answers only based on retrieved content, providing citations for verification. The paper details Ansari’s architecture, multi‑platform deployment, evaluation results (including top performance on the IslamicMMLU leaderboard and strong resistance to false premises), and lessons for faith‑sensitive LLM deployments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
6d ago

Hadith computational science in the age of large language models: a critical narrative review

The article reviews how transformer models, retrieval‑grounded pipelines, and large language models are reshaping hadith computational science. It critically evaluates existing literature, highlighting uneven progress: expanded data resources and mature segmentation tasks, yet persistent issues such as narrow corpora, weak benchmark comparability, and limited reproducibility. The authors argue that hadith computation should be viewed as an evidence‑infrastructure problem requiring knowledge integration, provenance, and expert supervision, and they propose a research agenda to strengthen the field’s methodological rigor.

By Md. Ashraful Haque (Greentech Apps Foundation, United Kingdom), Riasat Islam (Greentech Apps Foundation, United Kingdom, Queen Mary University of London, London, United Kingdom)
Hugging Face Trending Papers
Jul 22

HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering

Large language models (LLMs) can generate fluent Arabic answers, yet factual errors remain difficult to detect, localize, explain, and verify. Existing hallucination benchmarks often provide response-level labels, with limited support for identifying the exact erroneous content, explaining why it is incorrect, or selecting the correct factual answer.