Publications
For the most up-to-date list of my publications, please visit my Google Scholar profile.
IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions
- Type: Journal
- Badge: AI & Law
- Authors: Ezieddin Elmahjub, Junaid Qadir, Abdullah Mushtaq, Rafay Naeem, Ibrahim Ghaznavi, Waleed Iqbal
- Venue: Artificial Intelligence and Law (Springer), 2026
- Details: Open access. Received 30 November 2025, accepted 3 August 2026, published 17 September 2026.
- DOI: 10.1007/s10506-026-09535-4
- Links: Springer arXiv Leaderboard
WorldView-Bench: A Benchmark for Evaluating Global Cultural Perspectives in Large Language Models
- Type: Journal
- Badge: JAIR
- Authors: Abdullah Mushtaq, Imran Taj, Rafay Naeem, Ibrahim Ghaznavi, Junaid Qadir
- Venue: Journal of Artificial Intelligence Research (JAIR), 2026, Volume 85, Pages 28
- Details: Q1 journal, H-index 143, acceptance rate 12.6%.
- DOI: 10.1613/jair.1.19001
- Links: arXiv Code
Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content
- Type: Conference
- Badge: NeurIPS Workshop
- Authors: Abdullah Mushtaq, Rafay Naeem, Ezieddin Elmahjub, Ibrahim Ghaznavi, Shawqi Mohammed Al-Maliki, Mohamed Abdallah, Ala Al-Fuqaha, Junaid Qadir
- Venue: 5th Muslims in Machine Learning Workshop (MusIML) at NeurIPS 2025
- Links: arXiv Code
Harnessing Multi-Agent LLMs for Complex Engineering Problem-Solving: A Framework for Senior Design Projects
- Type: Conference
- Badge: EDUCON
- Authors: Abdullah Mushtaq, Rafay Naeem, Ibrahim Ghaznavi, M. Imran Taj, Imran Hashmi, Junaid Qadir
- Venue: IEEE Global Engineering Education Conference (EDUCON), 2025
- Links: arXiv Code
Toward Inclusive Educational AI: Auditing and Alignment of Frontier LLMs for Cultural Biases through a Multiplexity Lens
- Type: Conference
- Badge: EDUCON
- Authors: Abdullah Mushtaq, Rafay Naeem, M. Imran Taj, Ibrahim Ghaznavi, Junaid Qadir
- Venue: IEEE Global Engineering Education Conference (EDUCON), 2025
- Links: arXiv
Can Agents Judge Systematic Reviews Like Humans? Evaluating SLRs with LLM-based Multi-Agent System
- Type: Preprint
- Badge: arXiv
- Authors: Abdullah Mushtaq, Muhammad Rafay Naeem, Ibrahim Ghaznavi, Alaa Abd-alrazaq, Aliya Tabassum, Junaid Qadir
- Venue: arXiv preprint, 2025
- Details: In progress, in collaboration with Weill Cornell Medicine and Qatar University.
- Links: arXiv