PulseAugur
EN
LIVE 13:13:36

BART model fine-tuned for rubric-based C++ programming assignment grading

By PulseAugur Editorial · [3 sources] ·

Researchers have developed a method for automatically grading introductory C++ programming assignments using a fine-tuned BART transformer model. This approach incorporates rubric-based criteria and multitask learning to better mimic human instructor grading behavior. Experiments demonstrated that this rubric-guided training, particularly with boundary-based soft labels, achieved lower error rates and improved grade distribution alignment compared to standard methods. AI

IMPACT This research could lead to more accurate and instructor-aligned automated grading systems for programming courses.

RANK_REASON The cluster contains a research paper detailing a new method for automated grading using transformer models.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

BART model fine-tuned for rubric-based C++ programming assignment grading

COVERAGE [3]

  1. arXiv cs.AI TIER_1 English(EN) · Kelsey Rainey, Jesse Roberts ·

    Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria

    arXiv:2606.03814v1 Announce Type: new Abstract: This paper investigates rubric-aware, multitask fine-tuning of transformer models for automated grading of introductory C++ programming assignments, with the goal of producing grade predictions that better reflect instructor grading…

  2. arXiv cs.AI TIER_1 English(EN) · Jesse Roberts ·

    Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria

    This paper investigates rubric-aware, multitask fine-tuning of transformer models for automated grading of introductory C++ programming assignments, with the goal of producing grade predictions that better reflect instructor grading behavior than general-purpose LLMs. Using multi…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria

    This paper investigates rubric-aware, multitask fine-tuning of transformer models for automated grading of introductory C++ programming assignments, with the goal of producing grade predictions that better reflect instructor grading behavior than general-purpose LLMs. Using multi…

RELATED ENTITIES

RELATED TOPICS