VIHD detects hallucinations in medical MLLMs by identifying visually dominant decoder layers via probing and applying visual token masking to calibrate semantic entropy as a detection signal.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering
VIHD detects hallucinations in medical MLLMs by identifying visually dominant decoder layers via probing and applying visual token masking to calibrate semantic entropy as a detection signal.