9 papers
When AI Is Wrong on Purpose: How Students Respond to Buggy GenAI Code
Victor-Alexandru PÄdurean, Kaitlin Riegel, Alkis Gotovos +6
As Generative AI (GenAI) becomes increasingly central to software development, CS education is integrating prompt-centered workflows where students describe intended program behavi…
Understanding Student Perceptions, Mistakes, and Debugging Approaches when Solving Natural Language Programming Tasks
Victor-Alexandru PÄdurean, Kaitlin Riegel, Gweneth Barbre +7
Learning to communicate with code-generating AI models is an emerging skill for novice programmers. One recent pedagogical approach, Prompt Problems, has students solve computation…
Interleaving Natural Language Prompting with Code Editing for Solving Programming Tasks with Generative AI Models
Victor-Alexandru PÄdurean, Alkis Gotovos, Ahana Ghosh +5
Modern computing students often rely on both natural-language prompting and manual code editing to solve programming tasks. Yet we still lack a clear understanding of how these two…
The Right Kind of Help: Evaluating the Effectiveness of Feedback Methods in Elementary-Level Visual Programming
Ahana Ghosh, Liina Malva, Alkis Gotovos +2
We present a large-scale study comparing the effectiveness of various feedback methods in elementary-level programming. While prior work has explored different feedback methods, th…
Inference-Time Personalized Alignment with a Few User Preference Queries
Victor-Alexandru PÄdurean, Parameswaran Kamalaruban, Nachiket Kotalwar +2
We study the problem of aligning a generative model's response with a user's preferences. Recent works have proposed several different formulations for personalized alignment; howe…
Prompt Programming: A Platform for Dialogue-based Computational Problem Solving with Generative AI Models
Victor-Alexandru PÄdurean, Paul Denny, Alkis Gotovos +1
Computing students increasingly rely on generative AI tools for programming assistance, often without formal instruction or guidance. This highlights a need to teach students how t…