In an era where technological innovation progresses at an unprecedented pace, advancements in Artificial Intelligence (AI) are reshaping the landscape of higher education and knowledge systems at large. Large Language Models (LLMs) have become an indispensable part of daily interactions for millions of users, showcasing unparalleled proficiency in various natural language processing (NLP) tasks (Khandelwal et al., 2023). As these models permeate widespread usage, concerns emerge about their potential to encode and perpetuate societal biases, resulting in representational harms for users. This research aims to contribute to the ongoing discourse on LLM biases by conducting an empirical, comparative analysis of stereotypical bias levels between Eastern and Western contexts. The prevalence of Large Language Models in search engines, chatbot interfaces, and diverse applications has catapulted them into the mainstream, reaching global audiences. While their capabilities are undeniably impressive, the recognition of inherent risks linked to encoding biases from training data underscores the need to scrutinize these models, particularly in the context of societal and cultural variation