"When did the emperor Napoleon invented iPhone?" Such hallucination-inducing question is well known challenge in generative language modeling. In this study, we present an innovative concept of visual hallucination, referred to as "I Know (IK)" hallucination, to address scenarios where "I Don't Know" is the desired response. To effectively tackle this issue, we propose the VQAv2-IDK benchmark, the subset of VQAv2 comprising unanswerable image-question pairs as determined by human annotators. Stepping further, we present the visually dehallucinative instruction generation method for IK hallucination and introduce the IDK-Instructions visual instruction database. Our experiments show that current methods struggle with IK hallucination. Yet, our approach effectively reduces these hallucinations, proving its versatility across different frameworks and datasets.

在这项研究中，我们提出了一种创新的视觉幻觉概念，称为“我知道（IK）”幻觉，以解决所需回答为“我不知道”的场景。为了有效应对这个问题，我们提出了VQAv2-IDK基准，这是由人类标注人员确定的不可回答的图像问题对的子集。更进一步，我们提出了用于IK幻觉的视觉解幻指令生成方法，并介绍了IDK-Instructions视觉指令数据库。我们的实验证明了当前方法在处理IK幻觉时存在困难，然而我们的方法有效减少了这些幻觉，证明了它在不同框架和数据集上的多功能性。

视觉去想象指导生成：了解自己不知道的知识