What do models learn from training on more than text? Measuring visual commonsense knowledge

Anonymous

Abstract: There are limitations in learning language from text alone. Therefore, recent focus has been on developing multimodal models. However, few benchmarks exist that can measure what language models learn about language from multimodal training. We hypothesize that training on a visual modality should improve on the visual commonsense knowledge in language models. Therefore, we introduce two evaluation tasks for measuring visual commonsense knowledge in language models\footnote{A link to a GitHub repo with the evaluation tasks and code necessary for reproducing our results will be placed here. For reviewing purposes, we add it as supplementary material.} and use them to evaluate different multimodal models and unimodal baselines. Primarily, we find that the visual commonsense knowledge is not significantly different between the multimodal models and unimodal baseline models trained on visual text data.

Paper Type: short