文献类型：期刊文献

英文题名：Can Multimodal Large Language Models Understand Spatial Relations?

作者：Liu, Jingping[1]; Liu, Ziyan[1]; Cen, Zhedong[1]; Zhou, Yan[1]; Zou, Yinan[1]; Zhang, Weiyan[1]; Jiang, Haiyun[2]; Ruan, Tong[1]

机构：[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China; [2] School of Computer Science, Fudan University, Shanghai, China

年份：2025

外文期刊名：arXiv

收录：EI(收录号：20250231627)

语种：英文

外文关键词：Image understanding

摘要：Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or allowing questions to be answered using only the model’s prior knowledge without image understanding. To address these issues, we introduce SpatialMQA, a human-annotated spatial relation reasoning benchmark based on COCO2017, which enables MLLMs to focus more on understanding images in the objective world. To ensure data quality, we design a well-tailored annotation procedure, resulting in SpatialMQA consisting of 5,392 samples. Based on this benchmark, a series of closed- and open-source MLLMs are implemented and the results indicate that the current state-of-the-art MLLM achieves only 48.14% accuracy, far below the human-level accuracy of 98.40%. Extensive experimental analyses are also conducted, suggesting the future research directions. The benchmark and codes are available at https://github.com/ziyan-xiaoyu/SpatialMQA.git. Copyright ? 2025, The Authors. All rights reserved.