Hallucinated captions systematically improve VLM accuracy on vision-language tasks across nine models and nine datasets, with gains linked to broadened semantic coverage and modulated reasoning entropy.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
Hallucinated captions systematically improve VLM accuracy on vision-language tasks across nine models and nine datasets, with gains linked to broadened semantic coverage and modulated reasoning entropy.