1
Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers
多模态大模型解释比预测更难：新研究系统性评估概念解释作为ICL视觉分类器的有效性
arXiv:2605.28215v1 Announce Type: new Abstract: In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a f…