Search papers, labs, and topics across Lattice.
The paper introduces AICoFe, an AI-based collaborative feedback system for higher education that leverages a multi-LLM pipeline (GPT-4.1-mini, Gemini 2.5 Flash, and Llama 3.1) to generate actionable feedback from rubric data and qualitative observations. A "teacher-in-the-loop" workflow allows educators to refine AI-generated drafts, addressing the issue of inconsistent quality in student-generated peer feedback. The system's modular architecture and hybrid SQL/MongoDB data infrastructure ensure traceability and manage feedback versions.
Teachers can now scalably provide high-quality, personalized feedback to students by leveraging a multi-LLM system that synthesizes rubric data and qualitative observations, while retaining control through a teacher-in-the-loop workflow.
Effective peer feedback is essential for developing critical reflection in higher education, yet its impact is often limited by the inconsistent quality of student-generated comments. This paper presents the implementation and deployment of AICoFe (AI-based Collaborative Feedback), a system designed to bridge this gap through a human-centered AI approach. We describe a modular architecture that orchestrates a multi-LLM pipeline, utilizing GPT-4.1-mini, Gemini 2.5 Flash, and Llama 3.1, to synthesize quantitative rubric data and qualitative observations into coherent, actionable feedback. Key to the system is a"teacher-in-the-loop"mediation workflow, where educators use specialized Learning Analytics dashboards to curate and refine AI-generated drafts before delivery. Furthermore, we detail the underlying data infrastructure, which employs a hybrid SQL and MongoDB strategy to ensure traceability and manage semi-structured feedback versions.
