Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference
This work evaluates two mid-size LLMs on 23 richly annotated, expert-labeled episodes across prompting conditions that vary definitional scaffolding, reasoning mode, and turn structure, finding no single configuration performs best across all sensemaking dimensions.
Özge Alaçam, Zubeyde Demet Kirbulut Gunes, Funda Ekici et al.
· 0 citations