Researchers have developed a method to improve the automated grading of introductory C++ programming assignments by fine-tuning transformer models. This approach uses rubric-aware, multitask learning to better mimic instructor grading behavior than general-purpose large language models. Experiments demonstrated that a BART model, trained with rubric context and soft labels, achieved lower error rates and better alignment with empirical grade distributions compared to baseline methods. AI
IMPACT This research could lead to more nuanced and instructor-aligned automated grading systems for programming courses.
RANK_REASON Academic paper detailing a new methodology for automated grading using transformer models. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →