Adding retrieved textbook context drops LLaMA 3.2-Vision's zero-shot diagram-question accuracy on CK12-QA from 74% to 26%, while fine-tuning reverses the picture.
On opportunities and challenges of large multimodal foundation models in education,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Evaluating Multimodal Large Language Models on Educational Textbook Question Answering
Adding retrieved textbook context drops LLaMA 3.2-Vision's zero-shot diagram-question accuracy on CK12-QA from 74% to 26%, while fine-tuning reverses the picture.