MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems
MetaRA: 多模态大语言模型基于视觉问答系统的元形态鲁棒性评估
机构 * School of Computer Science and Engineering, Macau University of Science and Technology, Macao SAR(澳门科学技术大学计算机科学与工程学院) ; Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence, Wuhan University of Technology(湖北省交通物联网重点实验室,武汉理工大学)
专题命中 多模态评测 :multimodal(title,abstract);MLLM(abstract,abstract_cn);分类 cs.CV
AI总结 本文提出MetaRA,一种基于元形态测试的框架,用于评估多模态大语言模型基于视觉问答系统的鲁棒性,通过生成受控的图像-问题输入变体,揭示模型在语言扰动、视觉线索依赖和多模态推理中的弱点。