视觉-语言模型如何处理跨模态的冲突信息？
How Do Vision-Language Models Process Conflicting Information Across Modalities?
AI总结：
本文研究视觉-语言模型面对跨模态冲突输入时的行为，发现模型会偏袒特定模态，并揭示内部表示、注意力头及可迁移的模态无关路由头在冲突处理中的作用。
摘要：
AI模型越来越需要具备多模态能力，将不同的输入流整合为一致的状态表示，以便后续行为和动作可以基于该表示进行。本文旨在理解当输入流呈现冲突信息时，这类模型会如何表现。我们专门针对视觉-语言模型，提供不一致的输入（例如，一张狗的图片配以文字说明“一张猫的照片”），并要求模型报告其中一个特定模态中的信息（例如，“文字说明说了什么/图片中是什么？”）。我们发现，模型通常会偏袒一种模态而忽略另一种模态，例如，无论文字说明说什么都报告图片内容，但不同模型偏袒的模态有所不同。我们发现证据表明，行为上偏好的模态在模型内部表示结构中有所体现，并且特定的注意力头可以重构表示，使一种模态优先于另一种模态。此外，我们还发现了与模态无关的“路由头”，它们似乎会促进关于指令中所请求模态的回答，并且可以通过操纵或迁移这些路由头来提升跨数据集和跨模态的性能。总体而言，这项工作为识别和控制模型是否以及如何在复杂多模态环境中检测和解决冲突信号提供了关键步骤。
英文摘要：
AI models are increasingly required to be multimodal, integrating disparate input streams into a coherent state representation on which subsequent behaviors and actions can be based. This paper seeks to understand how such models behave when input streams present conflicting information. Focusing specifically on vision-language models, we provide inconsistent inputs (e.g., an image of a dog paired with the caption "A photo of a cat") and ask the model to report the information present in one of the specific modalities (e.g., "What does the caption say / What is in the image?"). We find that models often favor one modality over the other, e.g., reporting the image regardless of what the caption says, but that different models differ in which modality they favor. We find evidence that the behaviorally preferred modality is evident in the internal representational structure of the model, and that specific attention heads can restructure the representations to favor one modality over the other. Moreover, we find modality-agnostic "router heads" which appear to promote answers about the modality requested in the instruction, and which can be manipulated or transferred in order to improve performance across datasets and modalities. Together, the work provides essential steps towards identifying and controlling if and how models detect and resolve conflicting signals within complex multimodal environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
