Vision-language models exhibit literal superiority bias on noun compounds, with photorealistic visuals linked to poorer idiomatic grounding via new DIVA benchmark and Δ metric.
Task instructions.Annotators were instructed to evaluate each candidate along two dimensions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage
Vision-language models exhibit literal superiority bias on noun compounds, with photorealistic visuals linked to poorer idiomatic grounding via new DIVA benchmark and Δ metric.