Visual hallucination (VH) means that a multi-modal LLM (MLLM) imagines
incorrect details about an image in visual question answering. Existing studies
find VH instances only in existing image datasets, which results in biased
understanding of MLLMs' performance under VH due to limited diversity of such
VH instances. In this work, we propose a tool called VHTest to generate a
diverse set of VH instances. Specifically, VHTest finds some initial VH
instances in existing image datasets (e.g., COCO), generates a text description
for each VH mode, and uses a text-to-image generative model (e.g., DALL-E-3) to
generate VH images based on the text descriptions. We collect a benchmark
dataset with 1,200 VH instances in 8 VH modes using VHTest. We find that
existing MLLMs such as GPT-4V, LLaVA-1.5, and MiniGPT-v2 hallucinate for a
large fraction of the instances in our benchmark. Moreover, we find that
fine-tuning an MLLM using our benchmark dataset reduces its likelihood to
hallucinate without sacrificing its performance on other benchmarks. Our
benchmarks are publicly available: this https URL

通过使用一个工具称为 VHTest，我们生成了一个包含 8 种视觉幻觉模式的多样化 VH 实例数据集，并发现现有的多模态 LLM 如 GPT-4V，LLaVA-1.5 和 MiniGPT-v2 在我们的数据集中的大部分实例中出现幻觉，而使用我们的数据集对 MLLM 进行 fine-tuning 可以减少其幻觉可能性而不降低其在其他基准测试中的性能。