AI-Powered Virtual Student Advisor using language models in Generative AI

Start year: 2024

Summary: This project aims to develop an intelligent course advisor system prototype by employing large-scale language models (LLMs) and Retrieval-augmented generation (RAG) to replace the current difficult-to-navigate course advising service at an academic institute. The prototype will provide easy-to-understand and reliable information to help students find the necessary course and major information. Large language models, such as ChatGPT, generate generic answers and information that needs to be more specific in course advising. However, we will research several techniques to return the related answers in our proposed system by employing fine-tuning, Retrieval-augmented generation (RAG) strategies, and others. Based on the research and development, we will investigate the strengths and limitations of GenAI and embedding search algorithms in specific cases. Further, we will explore the ability to implement chain of thought models for reasoning questions.

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.