Multi-modal large language models (LLM) have achieved powerful capabilities for visual semantic understanding in recent years. However, little is known about how LLMs comprehend visual information and interpret different modalities of features. In this paper, we propose a new method for identifying multi-modal neurons in transformer-based multi-modal LLMs. Through a series of experiments, We highlight three critical properties of multi-modal neurons by four well-designed quantitative evaluation metrics. Furthermore, we introduce a knowledge editing method based on the identified multi-modal neurons, for modifying a specific token to another designative token. We hope our findings can inspire further explanatory researches on understanding mechanisms of multi-modal LLMs.

翻译：多模态大语言模型（LLM）近年来在视觉语义理解方面展现出强大能力。然而，关于LLM如何理解视觉信息并解释不同模态特征的内在机制仍鲜为人知。本文提出一种新方法，用于识别基于Transformer的多模态LLM中的多模态神经元。通过系列实验，我们借助四项精心设计的量化评估指标，揭示了多模态神经元的三个关键特性。进一步地，我们引入基于已识别多模态神经元的知识编辑方法，可将特定标记修改为另一目标标记。本研究的发现有望为深入理解多模态LLM机制的解释性研究提供启发。