Vision language models align poorly with human judgments of image relevance, but occasionally produce value-aware responses that human annotators missed.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vision Language Models as Values Detectors
Vision language models align poorly with human judgments of image relevance, but occasionally produce value-aware responses that human annotators missed.