Blogs (3) >>
Sat 23 Mar 2024 11:35 - 12:00 at Meeting Room E146 - LLM - Online Chair(s): Christopher Nitta

Large language models (LLMs) have shown promise in generating sensible code explanation and feedback in programming exercises. In this experience report, we discuss the process of using one of these models (OpenAI’s GPT-4) to generate individualized feedback for students’ Java code and pseudocode. We instructed GPT-4 to generate feedback for 113 submissions to four programming problems in an Algorithms and Data Structures class. We prompted the model with example feedback (few-shot learning) and instruction to (1) give feedback on conceptual understanding, syntax, and time complexity, and (2) suggest follow-up actions to build on students’ code or provide guiding questions. Overall, GPT-4 provided accurate feedback and successfully built on students’ ideas in most submissions. Human evaluators (computer science instructors and tutors) rated GPT-4’s hints as useful in guiding students’ next steps. Model performance varied with programming problems but not submission quality. We reflect on where the model performed well and fell short, and discuss the potential of integrating LLM-generated, individualized feedback into computer science instruction.

Sat 23 Mar

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

10:45 - 12:00
LLM - OnlinePapers at Meeting Room E146
Chair(s): Christopher Nitta University of California, Davis
10:45
25m
Talk
A Self-Regulated Learning Framework using Generative AI and its Application in CS Educational Intervention DesignOnlineGlobalIn-Person
Papers
Prajish Prasad FLAME University, Aamod Sane FLAME University
DOI
11:10
25m
Talk
Improvement in Program Repair Methods using Refactoring with GPT ModelsOnlineGlobalIn-Person
Papers
Ryosuke Ishizue NTT DATA Group Corporation / Waseda University, Kazunori Sakamoto WillBooster Inc. / Tokyo Online Unicersity / Waseda University, Hironori Washizaki Waseda University, Yoshiaki Fukazawa Waseda University
DOI
11:35
25m
Talk
Using GPT-4 to Provide Tiered, Formative Code FeedbackOnlineIn-Person
Papers
Ha Nguyen Utah State University, Vicki Allan Utah State University
DOI