#figurative-language

#figurative-language

We conduct human evaluation of generated explanations to more reliably assess their quality and identify key errors in multimodal figurative language understanding.

In developing V-FLUTE, we merge existing figurative datasets with human-AI collaboration to create a benchmark that enables AI models to understand visual entailment and figurative language.

Large AI models are improving in handling figurative language through datasets like FLUTE and V-FLUTE, which emphasize explainability in textual and multimodal settings.