2025 ASEE Annual Conference & Exposition

BOARD #129: AI as a Teaching Assistant: Aiding Engineering Students Beyond Office Hours

Presented at Poster Session-Electrical and Computer Engineering Division (ECE)

With the recent boom in artificial intelligence (AI) , AI has been added to countless tools to aid in our lives. As educators, we are interested in the possibility of applying recent developments of Generative AI models, particularly Large Language Models (LLMs), to help engineering students with their course work.

In this project, our goal is to get an AI program to act like a good Teaching Assistant (TA), providing a useful learning aid for students who have questions outside of office hours or for students who are not comfortable in office hours. This idea can perhaps also help where the TA budget is tight. Also, it might provide assistance for working engineers who are trying to learn on their own.

After proper training, the AI program ideally should answer correctly any class-related questions from a student. In our work, we are using course material for an undergraduate electrical-engineering course on transistor circuits. We have focused on early material on diode and transistor construction and operation, but we also tested the AI TA on some text-book chapters that cover single-transistor amplifiers.

In the paper, we will describe our approach to evaluating on-the-market models for this purpose, as well as, the training and fine-tuning of models to achieve a high-performance AI TA. We will present our evaluations of an AI TA’s ability to precisely point a student to sections in the given textbook as well as its ability to give a detailed explanation to a question, as a human TA would do. Limitations of the AI TA and potential extensions of this work will also be covered.

Authors

Mr. Ernest Wang University of California, Davis [biography]

Ernest Wang is a current undergraduate student in Electrical and Biomedical Engineering at the University of California, Davis. He is interested in the application of commercially available LLM models in helping engineering undergraduates with their studies. His other research interests include microfluidics and bioelectronics.
Harry Zhang University of California, Davis [biography]

Harry contributed to this research through the practical development and testing of the AI Teaching Assistant. He played a key role in implementing the AI TA and gathering the data used to evaluate its performance in answering Electrical Engineering student questions, as presented in this paper.
Prof. Paul J. Hurst University of California, Davis
Dr. Yubei Chen University of California, Davis [biography]

Yubei Chen is an assistant professor from the ECE department at UC Davis. He has worked with Professor Yann LeCun at Meta AI and NYU Center for Data Science as a postdoctoral researcher. Yubei received his MS/PhD in Electrical Engineering and Computer Sciences and MA in Mathematics at UC Berkeley under Professor Bruno Olshausen. His research interests span multiple aspects of representation learning. He explores the intersection of computational neuroscience and deep unsupervised learning, with the goal of improving our understanding of the computational principles governing unsupervised representation learning in both brains and machines, and reshaping our insights into natural signal statistics. He is a recipient of the NSF graduate fellowship, and ICLR Outstanding Paper Honorable Mention Award. You can learn more about him at https://yubeichen.com.
Kenneth Dyer Microsoft Corporation

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 22, 2025, and to all visitors after the conference ends on June 25, 2025

« View session

For those interested in:

Broadening Participation in Engineering and Engineering Technology