A Large-Scale Real-World Evaluation of LLM-Based Virtual Teaching Assistant

TL;DR

This study evaluates the effectiveness, student perceptions, and engagement patterns of a Large Language Model-based Virtual Teaching Assistant deployed in a real-world graduate course, providing insights into its practical impact and challenges.

Contribution

It presents the development and deployment of a large-scale LLM-based VTA in a real classroom, along with comprehensive interaction analysis and student perception surveys.

Findings

VTA effectively handled common student questions.

Student perceptions improved over time with VTA use.

Identified key challenges for broader adoption.

Abstract

Virtual Teaching Assistants (VTAs) powered by Large Language Models (LLMs) have the potential to enhance student learning by providing instant feedback and facilitating multi-turn interactions. However, empirical studies on their effectiveness and acceptance in real-world classrooms are limited, leaving their practical impact uncertain. In this study, we develop an LLM-based VTA and deploy it in an introductory AI programming course with 477 graduate students. To assess how student perceptions of the VTA's performance evolve over time, we conduct three rounds of comprehensive surveys at different stages of the course. Additionally, we analyze 3,869 student--VTA interaction pairs to identify common question types and engagement patterns. We then compare these interactions with traditional student--human instructor interactions to evaluate the VTA's role in the learning process. Through a large-scale empirical study and interaction analysis, we assess the feasibility of deploying VTAs in real-world classrooms and identify key challenges for broader adoption. Finally, we release the source code of our VTA system, fostering future advancements in AI-driven education: \texttt{https://github.com/sean0042/VTA}.