Introduces a rubric drawn from adaptive learning frameworks to assess VLMs on adaptivity, correctness, and quality in math instruction, finding measurable differences but inconsistent performance with limited learner information.
For large proprietary models (e.g., GPT-5), a one-time evaluation on 600 samples incurs a cost of approximately $6 for generating explanations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric Study
Introduces a rubric drawn from adaptive learning frameworks to assess VLMs on adaptivity, correctness, and quality in math instruction, finding measurable differences but inconsistent performance with limited learner information.