Patch-level analysis of token attention patterns and semantic alignment detects LVLM hallucinations at up to 90% accuracy by identifying diffuse, non-localized grounding that global methods miss.
Detecting and pre- venting hallucinations in large vision language models
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
-
Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
Patch-level analysis of token attention patterns and semantic alignment detects LVLM hallucinations at up to 90% accuracy by identifying diffuse, non-localized grounding that global methods miss.