LaViSA is a new benchmark that pairs structurally ambiguous sentences with images of their disambiguated meanings to evaluate VLMs on visual resolution of ambiguity.
Proceedings of the 10th Linguistic Annotation Workshop held in conjunction with
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
-
LaViSA: A Language and Vision Structural Ambiguity Benchmark
LaViSA is a new benchmark that pairs structurally ambiguous sentences with images of their disambiguated meanings to evaluate VLMs on visual resolution of ambiguity.