"UniChat: A Large Language Model based Chatbot to Answer University Related FAQs "

Abstract

"This final year project presents the development and evaluation of a Large Language Model (LLM) based chatbot designed to address student queries regarding universities. With the increasing complexity of university application processes and the plethora of information available, students often face challenges in obtaining accurate and timely information. Leveraging state-of-the-art natural language processing techniques, the chatbot provides an intuitive and interactive platform for students to inquire about various aspects of universities, including admissions, courses, facilities, and extracurricular activities. The system utilizes a pre-trained LLM to understand and generate responses to a wide range of questions, adapting its responses based on contextual cues and user interactions. Through a combination of supervised learning and reinforcement learning techniques, the chatbot continuously improves its performance and accuracy over time. Evaluation results demonstrate the effectiveness and utility of the chatbot in addressing student queries, with promising outcomes in terms of user satisfaction and information retrieval accuracy. This project contributes to the advancement of conversational AI technologies and offers a practical solution to support students in their university decision-making process."