In recent years large visual-language (V+L) models have achieved great success in various downstream tasks. However, it is not well studied whether these models have a conceptual grasp of the visual content. In this work we focus on conceptual understanding of these large V+L models. To facilitate this study, we propose novel benchmarking datasets for probing three different aspects of content understanding, 1) relations, 2) composition, and 3) context. Our probes are grounded in cognitive science and help determine if a V+L model can, for example, determine if snow garnished with a man is implausible, or if it can identify beach furniture by knowing it is located on a beach. We experimented with many recent state-of-the-art V+L models and observe that these models mostly fail to demonstrate a conceptual understanding. This study reveals several interesting insights such as that cross-attention helps learning conceptual understanding, and that CNNs are better with texture and patterns, while Transformers are better at color and shape. We further utilize some of these insights and investigate a simple finetuning technique that rewards the three conceptual understanding measures with promising initial results. The proposed benchmarks will drive the community to delve deeper into conceptual understanding and foster advancements in the capabilities of large V+L models. The code and dataset is available at: https://tinyurl.com/vlm-robustness

We propose a novel VQA dataset, BloomVQA, to facilitate comprehensive evaluation of large vision-language models on comprehension tasks. Unlike current benchmarks that often focus on fact-based memorization and simple reasoning tasks without theoretical grounding, we collect multiple-choice samples based on picture stories that reflect different levels of comprehension, as laid out in Bloom's Taxonomy, a classic framework for learning assessment widely adopted in education research. Our data maps to a novel hierarchical graph representation which enables automatic data augmentation and novel measures characterizing model consistency. We perform graded evaluation and reliability analysis on recent multi-modal models. In comparison to lowlevel tasks, we observe decreased performance on tasks requiring advanced comprehension and cognitive skills with up to 38.0% drop in VQA accuracy. In comparison to earlier models, GPT-4V demonstrates improved accuracy over all comprehension levels and shows a tendency of bypassing visual inputs especially for higher-level tasks. Current models also show consistency patterns misaligned with human comprehension in various scenarios, demonstrating the need for improvement based on theoretically-grounded criteria. The dataset can be accessed at https://huggingface. co/datasets/ygong/BloomVQA.