LLM-KCI: Leveraging Large Language Models to Identify Programming Knowledge Components
Open Access
- 18 February 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1557-1558
Abstract
Identifying Knowledge Components (KCs) in computer science education improves curriculum design and teaching strategies. We introduce a framework using Large Language Models to identify KCs from programming assignments automatically. Our framework helps educators align assignments with course objectives. GPT-4 identifies relevant KCs well, though there's a low match with expert-generated KCs at the course level. At the problem level, performance is lower, but key KCs are reasonably identified.Keywords
This publication has 2 references indexed in Scilit:
- Use of Large Language Models for Extracting Knowledge Components in CS1 Programming Exercises2024
- Context-Aware Analysis of Group Submissions for Group Anomaly Detection and Performance PredictionProceedings of the AAAI Conference on Artificial Intelligence, 2023