DISSECT benchmark reveals that VLMs extract visual details from scientific diagrams but frequently lose them during reasoning, with open-source models showing a larger integration gap than closed-source ones.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Post-generation control in AI-assisted math visual creation yields higher teacher ratings for predictability and correctness than pre- or mid-generation control, with qualitative trade-offs in agency and effort.
citing papers explorer
-
DISSECT: Diagnosing Where Vision Ends and Language Priors Begin in Scientific VLMs
DISSECT benchmark reveals that VLMs extract visual details from scientific diagrams but frequently lose them during reasoning, with open-source models showing a larger integration gap than closed-source ones.
-
When Should Teachers Control AI Generation for Mathematics Visuals?
Post-generation control in AI-assisted math visual creation yields higher teacher ratings for predictability and correctness than pre- or mid-generation control, with qualitative trade-offs in agency and effort.