The linguistic capabilities of Multimodal Large Language Models (MLLMs) are critical for their effective application across diverse tasks. This study aims to evaluate the performance of MLLMs on the VALSE benchmark, focusing on the efficacy of few-shot In-Context Learning (ICL), and Chain-of-Thought (CoT) prompting. We conducted a comprehensive assessment of state-of-the-art MLLMs, varying in model size and pretraining datasets. The experimental results reveal that ICL and CoT prompting significantly boost model performance, particularly in tasks requiring complex reasoning and contextual understanding. Models pretrained on captioning datasets show superior zero-shot performance, while those trained on interleaved image-text data benefit from few-shot learning. Our findings provide valuable insights into optimizing MLLMs for better grounding of language in visual contexts, highlighting the importance of the composition of pretraining data and the potential of few-shot learning strategies to improve the reasoning abilities of MLLMs.

对Multimodal Large Language Models在VALSE基准上的性能进行综合评估，发现In-Context Learning和Chain-of-Thought prompting能显著提升模型性能，尤其适用于需要复杂推理和语境理解的任务。同时，预训练数据集的组成和few-shot learning策略对模型优化都有重要影响。

评估多模态LLM在少样本学习中的语言能力