A vision-expert-filtered, chain-of-thought-guided, iteratively fine-tuned reward model boosts a compact 7B model's ability to judge vision-language responses, especially detecting hallucinations.
Silkie: Preference distillation for large visual language models, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
A vision-expert-filtered, chain-of-thought-guided, iteratively fine-tuned reward model boosts a compact 7B model's ability to judge vision-language responses, especially detecting hallucinations.