Unipa-GPT: Large Language Models for university-oriented QA in Italian
This is an incremental application of existing methods to a domain-specific problem for university students in Italy.
The paper tackles the problem of assisting students in choosing degree courses at the University of Palermo by developing Unipa-GPT, a chatbot based on gpt-3.5-turbo, using Retrieval Augmented Generation and fine-tuning, with results including comparisons and experimental outcomes from the SHARPER night event.
This paper illustrates the architecture and training of Unipa-GPT, a chatbot relying on a Large Language Model, developed for assisting students in choosing a bachelor/master degree course at the University of Palermo. Unipa-GPT relies on gpt-3.5-turbo, it was presented in the context of the European Researchers' Night (SHARPER night). In our experiments we adopted both the Retrieval Augmented Generation (RAG) approach and fine-tuning to develop the system. The whole architecture of Unipa-GPT is presented, both the RAG and the fine-tuned systems are compared, and a brief discussion on their performance is reported. Further comparison with other Large Language Models and the experimental results during the SHARPER night are illustrated. Corpora and code are available on GitHub