SIGCSE TS 2025 (series) / Posters /
LLM-KCI: Leveraging Large Language Models to Identify Programming Knowledge Components
This program is tentative and subject to change.
Fri 28 Feb 2025 10:00 - 12:00 at Exhibit Hall C - Posters - Posters #2
Identifying Knowledge Components (KCs) in computer science education improves curriculum design and teaching strategies. We introduce a framework using Large Language Models LLMs 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.
This program is tentative and subject to change.
Fri 28 FebDisplayed time zone: Eastern Time (US & Canada) change
Fri 28 Feb
Displayed time zone: Eastern Time (US & Canada) change