TY - GEN
T1 - Curriculum Planning for Independent Majors with Large Language Models
AU - Jin, Hyeon
AU - Yoon, Chaewon
AU - Song, Hyun Je
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - The independent major, also known as an individualized studies major or self-designed major, is a program for students whose academic goals cannot be met within standard department-specific curricula. This program enables students to design a customized, interdisciplinary course of study that aligns with their unique learning objectives. However, designing such a curriculum from a wide range of courses while ensuring alignment with these objectives and satisfying prerequisite requirements can be challenging. Additionally, students’ learning objectives may initially be vague, overly broad, or lack coherence across disciplines, making it difficult to design the curriculum. In this paper, we propose a curriculum planning method that leverages prerequisite relationships in traditional department-specific curricula and the capabilities of large language models (LLMs) to support independent majors. The proposed method first refines students’ learning objectives through LLM reasoning, then identifies relevant departments to obtain department-specific curricula and select core courses for each. These selected courses are expanded based on prerequisite relationships, combined into a structured curriculum, and transformed to comply with educational policies and accreditation standards. Experimental results from quantitative evaluations of previously implemented curricula and qualitative analyses by curriculum design experts demonstrate that the proposed method outperforms existing recommendation-based curriculum planning approaches.
AB - The independent major, also known as an individualized studies major or self-designed major, is a program for students whose academic goals cannot be met within standard department-specific curricula. This program enables students to design a customized, interdisciplinary course of study that aligns with their unique learning objectives. However, designing such a curriculum from a wide range of courses while ensuring alignment with these objectives and satisfying prerequisite requirements can be challenging. Additionally, students’ learning objectives may initially be vague, overly broad, or lack coherence across disciplines, making it difficult to design the curriculum. In this paper, we propose a curriculum planning method that leverages prerequisite relationships in traditional department-specific curricula and the capabilities of large language models (LLMs) to support independent majors. The proposed method first refines students’ learning objectives through LLM reasoning, then identifies relevant departments to obtain department-specific curricula and select core courses for each. These selected courses are expanded based on prerequisite relationships, combined into a structured curriculum, and transformed to comply with educational policies and accreditation standards. Experimental results from quantitative evaluations of previously implemented curricula and qualitative analyses by curriculum design experts demonstrate that the proposed method outperforms existing recommendation-based curriculum planning approaches.
KW - Curriculum planning
KW - Independent major
KW - Large language model
UR - https://www.scopus.com/pages/publications/105011947401
U2 - 10.1007/978-3-031-98417-4_33
DO - 10.1007/978-3-031-98417-4_33
M3 - Conference paper
AN - SCOPUS:105011947401
SN - 9783031984167
T3 - Lecture Notes in Computer Science
SP - 463
EP - 476
BT - Artificial Intelligence in Education - 26th International Conference, AIED 2025, Proceedings
A2 - Cristea, Alexandra I.
A2 - Walker, Erin
A2 - Lu, Yu
A2 - Santos, Olga C.
A2 - Isotani, Seiji
PB - Springer Science and Business Media Deutschland GmbH
T2 - 26th International Conference on Artificial Intelligence in Education, AIED 2025
Y2 - 22 July 2025 through 26 July 2025
ER -