Transforming Mentorship: An AI Powered Chatbot Approach to University Guidance

TL;DR

This work tackles the lack of personalized, on-demand undergraduate guidance by building a corpus-based AI chatbot for BRAC University. It integrates a data ingestion pipeline (CSV and web sources) with a hybrid retrieval module combining BM25 lexical ranking and ChromaDB semantic search, powered by the LLaMA-3.3-70B LLM to generate responses. The system achieves strong semantic alignment (BERTScore 0.831, METEOR 0.809) and demonstrates efficiency gains in data updates (106.82s vs 368.62s) over full re-ingestion, underscoring its practicality for scalable campus guidance. Evaluations using BLEU, ROUGE-L, BERTScore, and METEOR emphasize semantic fidelity over lexical overlap, supporting the approach's effectiveness for real-world advisory tasks. The work points to meaningful extensions, including multilingual support and knowledge graphs, to broaden applicability across universities.

Abstract

University students face immense challenges during their undergraduate lives, often being deprived of personalized on-demand guidance that mentors fail to provide at scale. Digital tools exist, but there is a serious lack of customized coaching for newcomers. This paper presents an AI-powered chatbot that will serve as a mentor for the students of BRAC University. The main component is a data ingestion pipeline that efficiently processes and updates information from diverse sources, such as CSV files and university webpages. The chatbot retrieves information through a hybrid approach, combining BM25 lexical ranking with ChromaDB semantic retrieval, and uses a Large Language Model, LLaMA-3.3-70B, to generate conversational responses. The generated text was found to be semantically highly relevant, with a BERTScore of 0.831 and a METEOR score of 0.809. The data pipeline was also very efficient, taking 106.82 seconds for updates, compared to 368.62 seconds for new data. This chatbot will be able to help students by responding to their queries, helping them to get a better understanding of university life, and assisting them to plan better routines for their semester in the open-credit university.

Figures (9)

• Figure 1: Distribution of Dataset.
• Figure 2: Word Cloud of Questions.
• Figure 3: Workflow of fetching webpages.
• Figure 4: Representation of unique record stored in Chroma DB.
• Figure 5: Workflow of Database Population.