II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models

Ziqiang Liu, Feiteng Fang, Xi Feng, Xeron Du, Chenhao Zhang, Noah Wang, yuelin bai, Qixuan Zhao, Liyang Fan, CHENGGUANG GAN, Hongquan Lin, Jiaming Li, Yuansheng Ni, Haihong Wu, Yaswanth Narsupalli, Zhigang Zheng, Chengming Li, Xiping Hu, Ruifeng Xu, Xiaojun Chen et al. (6 additional authors not shown)

Keywords: Multimodal, Image Understanding, Image Implication, Large Language Models

Abstract: The rapid advancements in the development of multimodal large language models (MLLMs) have consistently led to new breakthroughs on various benchmarks. In response, numerous challenging and comprehensive benchmarks have been proposed to more accurately assess the capabilities of MLLMs. However, there is a dearth of exploration of the higher-order perceptual capabilities of MLLMs. To fill this gap, we propose the Image Implication understanding Benchmark, II-Bench, which aims to evaluate the model's higher-order perception of images. Through extensive experiments on II-Bench across multiple MLLMs, we have made significant findings. Initially, a substantial gap is observed between the performance of MLLMs and humans on II-Bench. The pinnacle accuracy of MLLMs attains 74.8%, whereas human accuracy averages 90%, peaking at an impressive 98%. Subsequently, MLLMs perform worse on abstract and complex images, suggesting limitations in their ability to understand high-level semantics and capture image details. Finally, it is observed that most models exhibit enhanced accuracy when image sentiment polarity hints are incorporated into the prompts. This observation underscores a notable deficiency in their inherent understanding of image sentiment. We believe that II-Bench will inspire the community to develop the next generation of MLLMs, advancing the journey towards expert artificial general intelligence (AGI). II-Bench is publicly available at https://huggingface.co/datasets/m-a-p/II-Bench.

Flagged For Ethics Review: true

Submission Number: 1242