20.500.12556/DiRROS-22642 Automated grading through contrastive learning a gradient analysis and feature ablation approach As programming education becomes increasingly complex, grading student code has become a challenging task. Traditional methods, such as dynamic and static analysis, offer foundational approaches but often fail to provide granular insights, leading to inconsistencies in grading and feedback. This study addresses the limitations of these methods by integrating contrastive learning with explainable AI techniques to assess SQL code submissions. We employed contrastive learning to differentiate between student and correct SQL solutions, projecting them into a high-dimensional latent space, and used the Frobenius norm to measure the distance between these representations. This distance was used to predict the percentage of points deducted from each student’s solution. To enhance interpretability, we implemented feature ablation and integrated gradients, which provide insights into the specific tokens in student code that impact the grading outcomes. Our findings indicate that this approach improves the accuracy, consistency, and transparency of automated grading, aligning more closely with human grading standards. The results suggest that this framework could be a valuable tool for automated programming assessment systems, offering clear, actionable feedback and making machine learning models in educational contexts more interpretable and effective. automated programming assessment systems (APASs) contrastive learning explainable AI feature ablation integrated gradients machine learning in education natural language processing (NLP) avtomatizirani sistemi za ocenjevanje programerskih nalog kontrastno učenje razložljiva umetna inteligenca integrirani gradienti strojno učenje v izobraževanju strojno učenje obdelava naravnega jezika true false true MDPI Angleški jezik Slovenski jezik © 2025 by the authors Neznano 2025-06-12 04:06:02 2025-09-09 09:10:21 2025-10-24 03:51:52 0000-00-00 00:00:00 2025 0 0 Nasl. z nasl. zaslona; Opis vira z dne 11. 6. 2025; Soavtorji: Mario Fabijanić, Igor Mekterović and Leo Mršić; str. 1-24 iss. 2 Vol. 7 2025 0000-00-00 Zaloznikova NiDoloceno NiDoloceno 0000-00-00 0000-00-00 2025-04-29 004.85:37 2504-4990 10.3390/make7020041 239074051 https://www.mdpi.com/2504-4990/7/2/41 1 06d438b0-4721-11f0-bf0a-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=32811 RAZ_Sokac_Mateo_2025.pdf RAZ_Sokac_Mateo_2025.pdf 1 DB4D2106BCD7DABC77590E5E83493782 713748b8740cede8112dcb3353a070c46e867f3e73b1746f7fb4590ac666875f 7cc5c33e-8d4b-11f0-9bb7-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=34837 Rudolfovo – Znanstveno in tehnološko središče Novo mesto 0 0 0