Vision-Language Models like GPT-4, LLaVA, and CogVLM have surged in popularity recently due to their impressive performance in several vision-language tasks. Current evaluation methods, however, overlook an essential component: uncertainty, which is crucial for a comprehensive assessment of VLMs. Addressing this oversight, we present a benchmark incorporating uncertainty quantification into evaluating VLMs. Our analysis spans 20+ VLMs, focusing on the multiple-choice Visual Question Answering (VQA) task. We examine models on 5 datasets that evaluate various vision-language capabilities. Using conformal prediction as an uncertainty estimation approach, we demonstrate that the models' uncertainty is not aligned with their accuracy. Specifically, we show that models with the highest accuracy may also have the highest uncertainty, which confirms the importance of measuring it for VLMs. Our empirical findings also reveal a correlation between model uncertainty and its language model part.

翻译：诸如GPT-4、LLaVA和CogVLM等视觉-语言模型近年来因在多项视觉-语言任务中表现卓越而广受关注。然而，现有评估方法忽略了一个关键组成部分——不确定性，而这正是全面评估视觉-语言模型的核心要素。针对这一不足，我们提出一项将不确定性量化融入视觉-语言模型评估的基准。我们的分析涵盖20余种视觉-语言模型，聚焦于多项选择视觉问答任务，并在5个评估不同视觉-语言能力的数据集上检验模型性能。采用共形预测作为不确定性估计方法，我们证明模型的不确定性与其准确性并不对齐。具体而言，准确性最高的模型可能同时具有最高的不确定性，这证实了度量视觉-语言模型不确定性的重要性。实证结果还揭示了模型不确定性与其语言模型组件之间的相关性。