On an authentic Brazilian Portuguese residency exam, top general-purpose AI models scored near the human average on text-only questions but dropped when questions included medical images.
Procedure prediction from symbolic Electronic Health Records via time intervals analytics
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
-
Zero-shot Performance of Generative AI in Brazilian Portuguese Medical Exam
On an authentic Brazilian Portuguese residency exam, top general-purpose AI models scored near the human average on text-only questions but dropped when questions included medical images.