Antidote trains LVLMs to reject false presuppositions in questions and reduce object hallucination using synthetic images, self-corrected preferences, and a new CP-Bench benchmark.
Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
Antidote trains LVLMs to reject false presuppositions in questions and reduce object hallucination using synthetic images, self-corrected preferences, and a new CP-Bench benchmark.