AI models hallucinate when reading medical images and when generating them from text, producing false findings and anatomically impossible pictures.
Breaking the shield: Vulnerabilities in content moderation for multi- modal language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities
AI models hallucinate when reading medical images and when generating them from text, producing false findings and anatomically impossible pictures.