# Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference

arXiv: https://arxiv.org/abs/2609.31046 · HTML: https://mlsanity.com/paper/2609.31046/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs](https://mlsanity.com/paper/2409.16490/) (2024)
- [Towards Modeling Learner Performance with Large Language Models](https://mlsanity.com/paper/2403.14661/) (2024)
- [Can Language Models Follow Multiple Turns of Entangled Instructions?](https://mlsanity.com/paper/2503.13222/) (2025)
- [Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education](https://mlsanity.com/paper/2601.14560/) (2026)
- [Problems With Large Language Models for Learner Modelling: Why LLMs Alone Fall Short for Responsible Tutoring in K--12 Education](https://mlsanity.com/paper/2512.23036/) (2025)
- [RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generation](https://mlsanity.com/paper/2604.10960/) (2026)

## Abstract (arXiv)

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.