The study links three LVLM architectural dimensions to three hallucination types via a new benchmark, finding that language foundation quality reduces co-occurrence errors, visual encoder strength reduces similarity errors, alignment reduces uncertainty errors, and joint visual-alignment improvement
A comprehensive sur- vey of hallucination in large language, image, video and au- dio foundation models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
The paper defines the Conformal Hallucination Estimation Metric (CHEM) that localizes hallucination-prone regions in image reconstruction models via multiscale representations and distribution-free conformal regression.
citing papers explorer
-
What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
The study links three LVLM architectural dimensions to three hallucination types via a new benchmark, finding that language foundation quality reduces co-occurrence errors, visual encoder strength reduces similarity errors, alignment reduces uncertainty errors, and joint visual-alignment improvement
-
CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing
The paper defines the Conformal Hallucination Estimation Metric (CHEM) that localizes hallucination-prone regions in image reconstruction models via multiscale representations and distribution-free conformal regression.