Learning interpretable representations of data generative latent factors is
an important topic for the development of artificial intelligence. With the
rise of the large multimodal model, it can align images with text to generate
answers. In this work, we propose a framework to comprehensively explain each
latent factor in the generative models using a large multimodal model. We
further measure the uncertainty of our generated explanations, quantitatively
evaluate the performance of explanation generation among multiple large
multimodal models, and qualitatively visualize the variations of each latent
factor to learn the disentanglement effects of different generative models on
explanations. Finally, we discuss the explanatory capabilities and limitations
of state-of-the-art large multimodal models.

我们提出了一个框架，使用大型多模态模型全面解释生成模型中的每个潜在因子，并量化评估我们生成解释的不确定性，从而学习不同生成模型对解释的解缠效果，最后讨论最先进的大型多模态模型的解释能力和局限性。