Abstract
The recent advancements in auto-regressive multimodal large language models (MLLMs) have demonstrated promising progress for vision-language tasks. While there exists a variety of studies investigating the processing of linguistic information within large language models, little is currently known about the inner working mechanism of MLLMs and how linguistic and visual information interact within these models. In this study, we aim to fill this gap by examining the information flow between different modalities -- language and vision -- in MLLMs, focusing on visual question answering. Specifically, given an image-question pair as input, we investigate where in the model and how the visual and linguistic information are combined to generate the final prediction. Conducting experiments with a series of models from the LLaVA series, we find that there are two distinct stages in the process of integration of the two modalities. In the lower layers, the model first transfers the more general visual features of the whole image into the representations of (linguistic) question tokens. In the middle layers, it once again transfers visual information about specific objects relevant to the question to the respective token positions of the question. Finally, in the higher layers, the resulting multimodal representation is propagated to the last position of the input sequence for the final prediction. Overall, our findings provide a new and comprehensive perspective on the spatial and functional aspects of image and language processing in the MLLMs, thereby facilitating future research into multimodal information localization and editing.
Abstract (translated)
近期在自回归多模态大规模语言模型（MLLMs）方面的进展为视觉-语言任务展示了令人鼓舞的成果。虽然存在许多研究探讨了大型语言模型内部的语言信息处理机制，但对于MLLMs内部的工作机制以及这些模型中语言和视觉信息如何相互作用知之甚少。本研究旨在通过考察不同模态——语言和视觉之间在MLLMs中的信息流来填补这一空白，特别是关注于视觉问题回答任务。具体来说，在给定一幅图像-问题对作为输入的情况下，我们探讨了模型内部何处以及如何将视觉和语言信息结合起来生成最终预测。通过对LLaVA系列的一系列模型进行实验，我们发现两种模态的融合过程分为两个不同的阶段：在较低层中，模型首先将整个图像更一般的视觉特征转移到（语言）问题标记的表示上；在中间层，它再次将与问题相关的特定对象的视觉信息转移到问题的相关标记位置。最后，在较高层中，得到的多模态表征被传播到输入序列的最后一个位置以进行最终预测。总体而言，我们的发现为MLLMs中的图像和语言处理提供了新的、全面的空间和功能视角，从而促进了对未来多模态信息定位与编辑研究的支持。
URL
https://arxiv.org/abs/2411.18620
