Qu quantitative analysis of 622 peer reviews on review time, length, and correctness reveals that students are better at assessing actual correct submissions as correct than incorrect ones as incorrect, with test results and checklists slightly increasing their performance in identifying incorrect submissions.
A comparative analysis of six LLMs for generating formative feedback on introductory Java programs containing predefined defects under controlled conditions reveals substantial cross-model variation, particularly in multi-defect scenarios.
Melina Najimi, Saba Yazdani, Marzieh Ahmadzadeh· Proceedings of the Canadian...· 0 citations
The design and implementation of a web application that connects to a university version control system, analyzes student-selected repositories, and generates programming challenges targeted at weaknesses identified in the submitted source code is presented.
M. Horváth, Michaela Durkovicová, Lenka Bubenková et al.· International Computer Progr...· 0 citations
The system attained a System Usability Scale (SUS) score of 88.5 and cut grading time by 87.5 percent, facilitating focused instructor review in LLM-supported programming assessments, facilitating focused instructor review in LLM-supported programming assessments.
A. Ibrahim, Runal Rezkiawan· EDUMATIC: Jurnal Pendidikan...· 0 citations
A scaffolded programming exercise designed to support student differentiation between good and bad GenAI code suggestions based on negative expertise–that identifying why an answer is wrong is part of developing conceptual knowledge.
J. Prather, Stephen MacNeil, Andrew Luxton-Reilly et al.· International Computing Educ...· 0 citations
This Systematic Literature Review examines prompt engineering in automatic code generation using large language models (LLMs) and shows that prompt engineering has been established as a key discipline for optimizing interaction with LLMs and improve the accuracy, robustness, and applicability of the generated code.
E. Camacho, Y. Gutierrez, César Pardo· 0 citations
Findings are interpreted as evidence that course-aware style feedback is promising as a pre-submission revision aid, but that future versions should combine deterministic rule checks with LLM-generated explanations, rule citations, and stronger verification support.
Ethan Dickey, L. Vento, Peter Kurto et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
