We investigate the generalization boundaries of current Multimodal Large Language Models (MLLMs) via comprehensive evaluation under out-of-distribution scenarios and domain-specific tasks. We evaluate their zero-shot generalization across synthetic images, real-world distributional shifts, and specialized datasets like medical and molecular imagery. Empirical results indicate that MLLMs struggle with generalization beyond common training domains, limiting their direct application without adaptation. To understand the cause of unreliable performance, we analyze three hypotheses: semantic misinterpretation, visual feature extraction insufficiency, and mapping deficiency. Results identify mapping deficiency as the primary hurdle. To address this problem, we show that in-context learning (ICL) can significantly enhance MLLMs' generalization, opening new avenues for overcoming generalization barriers. We further explore the robustness of ICL under distribution shifts and show its vulnerability to domain shifts, label shifts, and spurious correlation shifts between in-context examples and test data.

翻译：我们通过全面的分布外场景及领域特定任务评估，探究当前多模态大语言模型（MLLMs）的泛化边界。具体评测了模型在合成图像、真实世界分布偏移以及医学和分子影像等专业数据集上的零样本泛化能力。实验结果表明，MLLMs在超出常见训练域的泛化任务中表现欠佳，这限制了其未经适配时的直接应用。为揭示性能不稳定的成因，我们提出三种假设：语义误解、视觉特征提取不足以及映射缺陷。结果证实映射缺陷是主要瓶颈。针对该问题，我们发现上下文学习（ICL）可显著增强MLLMs的泛化能力，为突破泛化壁垒开辟新路径。进一步探究ICL在分布偏移下的鲁棒性时，我们发现其对领域偏移、标签偏移以及上下文示例与测试数据之间的虚假相关偏移均存在脆弱性。