Fine-Tuned Large Language Models for Enhanced Automated Academic Advising
Document Type
Conference Proceeding
Source of Publication
IEEE Global Engineering Education Conference Educon
Publication Date
6-3-2025
Abstract
The rapid increase in student enrollment at universities across the UAE has underscored the limitations of traditional academic advising methods, including long wait times and overburdened advisors. This paper presents a finetuned Academic Advisor Chatbot leveraging the 'noushermes2' large language model (LLM) to deliver real-time, context-aware guidance tailored to the university's academic policies. By integrating institution-specific data, the chatbot addresses common student queries with high accuracy and clarity, as evidenced by BLEU scores improving from 0.45 to 0.78 and ROUGE-L scores reaching 0.85 for specific academic scenarios. A user feedback study involving 50 students revealed high satisfaction levels, with an average rating of 4.6/5 for accuracy, 4.7/5 for clarity, and 4.8/5 for time efficiency. The chatbot not only enhances the course registration experience but also reduces advisor workload, offering a scalable solution to meet the needs of a growing student population. Future enhancements will focus on multilingual support and expanded program-specific datasets to further improve usability and inclusivity.
DOI Link
ISBN
[9798331539498]
ISSN
Publisher
IEEE
Disciplines
Computer Sciences | Education
Keywords
Academic Advising, Chatbot, Large Language Models, LLM Fine-tuning, Natural Language Processing (NLP)
Scopus ID
Recommended Citation
Ismail, Heba, "Fine-Tuned Large Language Models for Enhanced Automated Academic Advising" (2025). All Works. 7429.
https://zuscholars.zu.ac.ae/works/7429
Indexed in Scopus
yes
Open Access
no