LLM-Assisted, Iterative Curriculum Writing: A Human-Centered AI Approach in Finnish Higher Education
Year: 2025
Type: conference-paper
Abstract: This paper presents a Large Language Model (LLM)-based system designed to support curriculum development, iteratively refined through extensive user testing and deployed within a major Finnish higher education institution over the past two years.Distinct from typical content generation tools, our system facilitates iterative human-AI collaboration by providing structured suggestions and analyzing course descriptions for alignment with institutional goals, accreditation requirements, and competency frameworks.We investigate how such a tool can reduce educators' cognitive load while preserving human expertise, detailing the system's technical architecture and iterative development grounded in a human-centered design approach.This involved prototyping, workshops, and user testing with curriculum coordinators and faculty across diverse departments.We present detailed findings, including quantitative metrics, qualitative feedback, and user quotes, demonstrating the system's evolving reception and potential to support complex educational planning tasks.
Authors: Leo Huovinen, Mika Hämäläinen
Institution: Helsinki Metropolia University of Applied Sciences
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W4412889246