Blogs (19) >>
Fri 17 Mar 2023 16:10 - 16:35 at 713 - Technology-Enabled Instruction Chair(s): Barbara Ericson

Advances in natural language processing have resulted in large language models (LLMs) that are capable of generating understandable and sensible written text. Recent versions of these models, such as OpenAI Codex and GPT-3, can generate code and code explanations. However, it is unclear whether and how students might engage with such explanations. In this paper, we report on our experiences generating multiple code explanation types using LLMs and integrating them into an interactive e-book on web software development. We modified the e-book to make LLM-generated code explanations accessible through buttons next to code snippets in the materials, which allowed us to track the use of the explanations as well as to ask for feedback on their utility. Three different types of explanations were available for students for each explainable code snippet; a line-by-line explanation, a list of important concepts, and a high-level summary of the code. Our preliminary results show that all varieties of explanations were viewed by students and that the majority of students perceived the code explanations as helpful to them. However, student engagement appeared to vary by code snippet complexity, explanation type, and code snippet length. Drawing on our experiences, we discuss future directions for integrating explanations generated by LLMs into existing computer science classrooms.

Fri 17 Mar

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

15:45 - 17:00
Technology-Enabled InstructionPapers at 713
Chair(s): Barbara Ericson University of Michigan
15:45
25m
Paper
Discovering, Autogenerating, and Evaluating Distractors for Python Parsons Problems in CS1In-Person
Papers
David Smith University of Illinois at Urbana-Champaign, Craig Zilles University of Illinois at Urbana-Champaign
DOI
16:10
25m
Paper
Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-BookIn-PersonGlobal
Papers
Stephen MacNeil Temple University, Andrew Tran Temple University, Arto Hellas Aalto University, Joanne Kim Temple University, Sami Sarsa Aalto University, Paul Denny The University of Auckland, Seth Bernstein Temple University, Juho Leinonen The University of Auckland
DOI
16:35
25m
Paper
FalconCode: A Multiyear Dataset of Python Code Samples from an Introductory Computer Science CourseIn-Person
Papers
Adrian de Freitas USAF Academy, Joel Coffman United States Air Force Academy, Michelle de Freitas Academy School District 20, Justin Wilson USAF Academy, Troy Weingart United Stated Air Force Academy Dept of Computer Science
DOI