PulseAugur
EN
LIVE 05:45:49

BART model fine-tuned for more accurate programming assignment grading

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]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  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…