Abstract
Collaborative science learning requires nuanced interpretation of student dialogue to characterize how learners identify knowledge gaps, build explanations, and work toward resolution - a theory-driven analysis that is labor-intensive and difficult to scale. We investigate whether instruction-tuned large language models (LLMs) can support multidimensional analysis of collaborative sensemaking without task-specific training, and whether structured knowledge-state information improves model inference. We evaluate two mid-size LLMs on 23 richly annotated, expert-labeled episodes across prompting conditions that vary definitional scaffolding, reasoning mode, and turn structure. Without reasoning, models tend to overpredict successful sensemaking; reasoning-enabled prompting improves identification of unsuccessful cases. Knowledge-state diagnostics provide additional grounding, improving detection of unsuccessful sensemaking and increasing agreement with expert annotations. No single configuration performs best across all sensemaking dimensions, underscoring the multidimensional nature of the task.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Alacam, Ö., Güneş, Z. D. K., Ekici, F., Turan-Oluk, N., Dinçdemir, D., Kadayıfçı, H., Yeşiloğlu, S. N., Işık, B., Tümay, H., & Gencer, S. (2026). Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference. https://omanscience.com/en/articles/modeling-student-sensemaking-with-llms-and-knowledge-graph-guided-inference
MLA 9
Alacam, Özge, et al. "Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference." https://omanscience.com/en/articles/modeling-student-sensemaking-with-llms-and-knowledge-graph-guided-inference.
Chicago (author–date)
Alacam, Özge, Zübeyde Demet Kirbulut Güneş, Funda Ekici, Nurcan Turan-Oluk, Dilay Dinçdemir, Hakkı Kadayıfçı, Sevinç Nihal Yeşiloğlu, Burcu Işık, Halil Tümay, and Sinem Gencer. 2026. "Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference." https://omanscience.com/en/articles/modeling-student-sensemaking-with-llms-and-knowledge-graph-guided-inference.
Harvard
Alacam, Ö., Güneş, Z. D. K., Ekici, F., Turan-Oluk, N., Dinçdemir, D., Kadayıfçı, H., Yeşiloğlu, S. N., Işık, B., Tümay, H. and Gencer, S. (2026) 'Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference', Available at: https://omanscience.com/en/articles/modeling-student-sensemaking-with-llms-and-knowledge-graph-guided-inference.
Vancouver
Alacam Ö, Güneş ZDK, Ekici F, Turan-Oluk N, Dinçdemir D, Kadayıfçı H, et al. Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference. https://omanscience.com/en/articles/modeling-student-sensemaking-with-llms-and-knowledge-graph-guided-inference
IEEE
Ö. Alacam, Z. D. K. Güneş, F. Ekici, N. Turan-Oluk, D. Dinçdemir, H. Kadayıfçı, S. N. Yeşiloğlu, B. Işık, H. Tümay, and S. Gencer, "Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference," https://omanscience.com/en/articles/modeling-student-sensemaking-with-llms-and-knowledge-graph-guided-inference.