Transforming Mentorship: An AI Powered Chatbot Approach to University Guidance

2025-11-06

AI Summary

To address the lack of personalized, real-time academic guidance for freshmen, this study develops an AI-powered intelligent tutoring system tailored for undergraduate students. Methodologically, we propose a hybrid retrieval framework integrating BM25 and ChromaDB, enabling efficient data ingestion from heterogeneous campus sources—including CSV files and web pages—with average update latency of 106.82 seconds. Responses are generated using the LLaMA-3.3-70B large language model, augmented by semantic retrieval to enhance answer precision. Experimental evaluation demonstrates high semantic relevance of system outputs (BERTScore: 0.831; METEOR: 0.809), significantly outperforming baseline approaches. Our key contributions include: (1) a lightweight, dynamically evolvable campus knowledge retrieval architecture; and (2) the first end-to-end intelligent academic guidance system providing adaptive, full-lifecycle support specifically designed for freshmen.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Intelligent User Interfaces
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Providing personalized on-demand university guidance for students lacking mentorship
• Addressing the lack of customized coaching for university newcomers at scale
• Developing an AI-powered chatbot to assist students with academic planning

Innovation

• AI chatbot using LLaMA-3.3-70B for conversational responses
• Hybrid retrieval combining BM25 and ChromaDB semantic search
• Efficient data pipeline processing diverse university information sources