Decomposing MLLM responses into atomic verification tasks and checking them with an ensemble of open-source expert models yields preference data that reduces hallucination in LLaVA and Qwen-VL-Chat.
Llama 3.1 8b instruct
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Decompose and Leverage Preferences from Expert Models for Improving Trustworthiness of MLLMs
Decomposing MLLM responses into atomic verification tasks and checking them with an ensemble of open-source expert models yields preference data that reduces hallucination in LLaVA and Qwen-VL-Chat.