Open Collections

Haaben, Ferdinand

This research addresses the challenge of maintaining high-quality student-educator interaction amidst increasing class sizes and repetitive queries. Recognizing the prominent role of direct contact with teaching staff in improving student outcomes, this research presents the integration of a retrieval-augmented generation (RAG)-based large language model (LLM) into an existing online learning platform. The AI system is designed to provide immediate, interactive responses to student questions, which instructors can subsequently review and validate. Additionally, the system makes use of various sorting and filtering techniques to make finding answers as easy as possible. The approach aims to provide students with immediate answers while mitigating the risks of misinformation by keeping educators in the feedback loop. The thesis proposes a study to measure the effectiveness of the system in reducing redundant communication and improving the student experience.

Text

University of British Columbia. COSC 449

Vancouver : University of British Columbia Library

10.14288/1.0443555

Science, Irving K. Barber Faculty of (Okanagan); Computer Science, Mathematics, Physics and Statistics, Department of (Okanagan)

Undergraduate

http://creativecommons.org/licenses/by-nc-nd/4.0/