揭示视觉语言模型如何用线性特征表示图像，且深层特征更共享。
Line of Sight: On Linear Representations in VLLMs
- 通过线性可解码方法分析模型隐藏层中的图像特征。
- 在深层网络中发现图像概念的线性特征占比显著提升。
- 构建稀疏自编码器增强可解释性，适合研究多模态表征的学者。
通过微调视觉输入嵌入，语言模型可获得多模态能力。但这类模型如何在隐藏激活中表示图像？我们研究了主流开源视觉语言模型 LlaVA-Next 中的图像概念表征。发现多种 ImageNet 类别可通过残差流中的线性可解码特征表示。通过针对性修改输出验证这些特征具有因果性。为提升线性特征多样性，我们训练了多模态稀疏自编码器（SAEs），构建出包含文本与图像特征的高可解释词典。尽管跨模态表征初始差异明显，但随着网络加深，共享特征逐渐增多。
原文摘要 · Abstract (English)
Language models can be equipped with multimodal capabilities by fine-tuning on embeddings of visual inputs. But how do such multimodal models represent images in their hidden activations? We explore representations of image concepts within LlaVA-Next, a popular open-source VLLM. We find a diverse set of ImageNet classes represented via linearly decodable features in the residual stream. We show that the features are causal by performing targeted edits on the model output. In order to increase the diversity of the studied linear features, we train multimodal Sparse Autoencoders (SAEs), creating a highly interpretable dictionary of text and image features. We find that although model representations across modalities are quite disjoint, they become increasingly shared in deeper layers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。