NOVI : Chatbot System for University Novice with BERT and LLMs

TL;DR

This paper introduces NOVI, a chatbot system based on GPT-4o and BERT, designed to assist university freshmen in adapting to campus life by leveraging community data and evaluated with multiple NLP metrics.

Contribution

The paper presents a novel chatbot system tailored for university newcomers, utilizing LLMs and community data, and evaluates its performance with comprehensive NLP metrics.

Findings

NOVI effectively assists freshmen in social adaptation.

The system demonstrates promising performance based on BLEU, ROUGE, and METEOR scores.

Potential applications extend to various adaptation scenarios.

Abstract

To mitigate the difficulties of university freshmen in adapting to university life, we developed NOVI, a chatbot system based on GPT-4o. This system utilizes post and comment data from SKKU 'Everytime', a university community site. Developed using LangChain, NOVI's performance has been evaluated with a BLEU score, Perplexity score, ROUGE-1 score, ROUGE-2 score, ROUGE-L score and METEOR score. This approach is not only limited to help university freshmen but is also expected to help various people adapting to new environments with different data. This research explores the development and potential application of new educational technology tools, contributing to easier social adaptation for beginners and settling a foundation for future advancement in LLM studies.