Blogs (3) >>

This program is tentative and subject to change.

Sat 1 Mar 2025 11:22 - 11:41 at Meeting Room 406 - Upper-level Undergraduate Courses

Large language models (LLMs) are already heavily used by professional software engineers. An important skill for new university graduates to possess will be the ability to use such LLMs to effectively navigate and modify a large code base. While much of the prior work related to LLMs focuses on students learning to program, less work has focused on the student experience and trust in using these tools, especially while working with large code bases. In this study, we taught students about various Github Copilot features, including Copilot chat, in an upper-division software engineering course and asked students to add a feature to a large code base using Copilot. Our analysis revealed a new interaction pattern that we call textit{one-shot prompting}, in which students ask Copilot to implement the entire feature at once and spend the next few prompts asking Copilot to debug the code or asking Copilot to regenerate its incorrect response. Finally, students reported significantly more trust in the code comprehension features than code generation features of Copilot, perhaps due to the presence of trust affordances in the Copilot chat that are absent in the code generation features. Our study contributes to our understanding of how students interact with LLMs for working with large code bases, provides implications for educators and researchers, and suggests design recommendations for existing LLMs.

This program is tentative and subject to change.

Sat 1 Mar

Displayed time zone: Eastern Time (US & Canada) change

10:45 - 12:00
Upper-level Undergraduate CoursesPapers at Meeting Room 406
10:45
18m
Talk
Creating a Quantum Programming Course from Scratch: A Computer Science Professor’s Journey
Papers
Joshua T. Guerin University of Northern Colorado
11:03
18m
Talk
Diary study as an educational tool: An experience report from an HCI course
Papers
Jixiang Fan Virginia Tech, Derek Haqq Virginia Tech, Morva Saaty Virginia Tech, Wei Lu Wang Virginia Tech, Scott McCrickard Virginia Tech
11:22
18m
Talk
Students' Use of GitHub Copilot for Working with Large Code Bases
Papers
Anshul Shah University of California, San Diego, Anya Chernova University of California, San Diego, Elena Tomson University of California, San Diego, Leo Porter University of California San Diego, William Griswold UC San Diego, Adalbert Gerald Soosai Raj University of California San Diego
11:41
18m
Talk
Teaching Cloud Infrastructure and Scalable Application Deployment in an Undergraduate Computer Science Program
Papers
Aditya Saligrama Stanford University, Cody Ho Stanford University, Benjamin Tripp Stanford University, Michael Abbott Stanford University, Christos Kozyrakis Stanford University, USA