2 papers
cs.CY2026
Simulating Validity: Modal Decoupling in MLLM Generated Feedback on Science Drawings
Arne Bewersdorff, Nejla Yuruk, Xiaoming Zhai
In science education, students frequently construct hand-drawn visual models of scientific phenomena. These drawings rely on a visual structure where information is encoded through…
cs.AI2025
Using Large Language Models to Assess Teachers' Pedagogical Content Knowledge
Yaxuan Yang, Shiyu Wang, Xiaoming Zhai
Assessing teachers' pedagogical content knowledge (PCK) through performance-based tasks is both time and effort-consuming. While large language models (LLMs) offer new opportunitie…