Dual attention plus a learned null-image prompt reduces reported hallucination rates in LLaVA-1.5, but the gains rely on test-set-tuned hyperparameters.
Are we on the right way for evaluating large vision-language models?, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance
Dual attention plus a learned null-image prompt reduces reported hallucination rates in LLaVA-1.5, but the gains rely on test-set-tuned hyperparameters.