Sadeque, Farig YousufHossain, Kazi AbrabMahmud, Jannatul SomiyaTuli, Maria HossainMitra, Anik2026-01-122026-01-1220252025-10ID 21201496ID 22101698ID 22101788ID 22101426http://hdl.handle.net/10361/27421Cataloged from PDF version of thesis.Includes bibliographical references (pages 60-63).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2025.While recent developments in large language models have improved bias detection and classification, sensitive subjects like religion still present challenges because even minor errors can result in severe misunderstandings. In particular, multilingual models often misrepresent religions and have difficulties being accurate in religious contexts. To address this, we 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 three different types of prompts in both English and Bengali. Our results indicate that models perform better in English than in Bengali and consistently display bias toward Islam, even when answering religion-neutral questions. These findings highlight persistent bias in multilingual models when similar questions are asked in different languages.78 pagesenBRAC University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Large language modelsMultilingual modelsBias detectionReligious biasAINatural language processingNatural language processing (Computer science).Linguistic analysis (Linguistics)--Data processing.Artificial intelligence.Natural language generation (Computer science).Content analysis (Communication).Thesis