Leveraging Peer, Self, and Teacher Assessments for Generative AI-Enhanced Feedback

TL;DR

This study explores how a GenAI-enhanced feedback system can effectively integrate teacher, peer, and self-assessments to improve feedback quality and scalability in higher education, supported by empirical analysis of evaluation data.

Contribution

It introduces a novel GenAI model within the AICoFe system that combines multiple assessment sources for more valid and transparent feedback in large courses.

Findings

High overall agreement among assessment sources

Systematic variations in scoring behavior identified

Enhanced GenAI model improves feedback integration

Abstract

Providing timely and meaningful feedback remains a persistent challenge in higher education, especially in large courses where teachers must balance formative depth with scalability. Recent advances in Generative Artificial Intelligence (GenAI) offer new opportunities to support feedback processes while maintaining human oversight. This paper presents an study conducted within the AICoFe (AI-based Collaborative Feedback) system, which integrates teacher, peer, and self-assessments of engineering students' oral presentations. Using a validated rubric, 46 evaluation sets were analyzed to examine agreement, correlation, and bias across evaluators. The analyses revealed consistent overall alignment among sources but also systematic variations in scoring behavior, reflecting distinct evaluative perspectives. These findings informed the proposal of an enhanced GenAI model within AICoFe system, designed to integrate human assessments through weighted input aggregation, bias detection, and context-aware feedback generation. The study contributes empirical evidence and design principles for developing GenAI-based feedback systems that combine data-based efficiency with pedagogical validity and transparency.