Alam, Md. AhasanulPayel, Nehrin SiddiqueMostafa, MD Tanjim2025-05-122025-05-1220242024-06ID 16201084http://hdl.handle.net/10361/25879Cataloged from PDF version of thesis.Includes bibliographical references (pages 21-24).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.Large language models are powerful tools that can be used in variety of tasks, including text generation, translation and question answering. However, Language models tend to pick up undesirable biases from the training data. Due to the rapid advancement in artificial intelligence and due to the widespread use of these models, we risk amplifying social stereotypes and biases through these systems. Word embedding is a framework that represents text data as vectors allowing them to capture the context of each word within a large text corpora. Word embeddings are essentially the building blocks of popular Bangla language models such as Bangla Glove, Bangla word2vec, banglaBERT. We observe that gender bias exists in a geometric direction in the word embedding. Using methods such as Principal component analysis, Word Embedding Association Test and Mask Language Modelling, we highlight the presence of stereotypically biased associations in the word embeddings. Our findings have broader implications for AI research within the Bangla NLP community and for enhancing both the viability and usability of Bangla NLP systems for downstream tasks.33 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 modelsNatural language processingGender biasWord embeddingsMachine learningBanglaBERTNatural language processing (Computer science).Deep learning (Machine learning).Neural networks (Computer science).Computational linguistics.Text data mining.Thesis