A contrastive self-judgment score that subtracts a model's image-free confidence from its visual confidence is used to guide decoding, safety moderation, and DPO training, improving hallucination and safety metrics across LVLMs.
Title resolution pending
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
-
Improving Alignment in LVLMs with Debiased Self-Judgment
A contrastive self-judgment score that subtracts a model's image-free confidence from its visual confidence is used to guide decoding, safety moderation, and DPO training, improving hallucination and safety metrics across LVLMs.