promising

Authors: Hugo Roger Paz

Abstract: In technical subjects characterized by high enrollment, such as Basic Hydraulics, the assessment of reports necessitates superior levels of objectivity, consistency, and formative feedback; goals often compromised by faculty workload. This study presents the implementation of a generative artificial intelligence (AI) assisted assessment system, supervised by instructors, to grade 33 hydraulics reports. The central objective was to quantify its impact on the efficiency, quality, and fairness of the process. The employed methodology included the calibration of the Large Language Model (LLM) with a detailed rubric, the batch processing of assignments, and a human-in-the-loop validation phase. The quantitative results revealed a noteworthy 88% reduction in grading time (from 50 to 6 minutes per report, including verification) and a 733% increase in productivity. The quality of feedback was substantially improved, evidenced by 100% rubric coverage and a 150% increase in the anchoring of comments to textual evidence. The system proved to be equitable, exhibiting no bias related to report length, and highly reliable post-calibration (r = 0.96 between scores). It is concluded that the hybrid AI-instructor model optimizes the assessment process, thereby liberating time for high-value pedagogical tasks and enhancing the fairness and quality of feedback, in alignment with UNESCO’s principles on the ethical use of AI in education.

Link: https://arxiv.org/abs/2510.22286

Authors: Omar Alsaiari, Nilufar Baghaei, Jason M. Lodge, Omid Noroozi, Dragan Gašević, Marie Boden, Hassan Khosravi

Abstract: Feedback is one of the most powerful influences on student learning, with extensive research examining how best to implement it in educational settings. Increasingly, feedback is being generated by artificial intelligence (AI), offering scalable and adaptive responses. Two widely studied approaches are directive feedback, which gives explicit explanations and reduces cognitive load to speed up learning, and metacognitive feedback which prompts learners to reflect, track their progress, and develop self-regulated learning (SRL) skills. While both approaches have clear theoretical advantages, their comparative effects on engagement, confidence, and quality of work remain underexplored. This study presents a semester-long randomised controlled trial with 329 students in an introductory design and programming course using an adaptive educational platform. Participants were assigned to receive directive, metacognitive, or hybrid AI-generated feedback that blended elements of both directive and metacognitive feedback. Results showed that revision behaviour differed across feedback conditions, with Hybrid prompting the most revisions compared to Directive and Metacognitive. Confidence ratings were uniformly high, and resource quality outcomes were comparable across conditions. These findings highlight the promise of AI in delivering feedback that balances clarity with reflection. Hybrid approaches, in particular, show potential to combine actionable guidance for immediate improvement with opportunities for self-reflection and metacognitive growth.

Link: https://arxiv.org/abs/2510.19685