Can Multimodal Large Language Models Understand Spatial Relations?
Jingping Liu, Ziyan Liu, Zhedong Cen, Yan Zhou, Yinan Zou, Weiyan Zhang, Haiyun Jiang, Tong Ruan
Abstract
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://huggingface.co/datasets/liuziyan/SpatialMQA.
BibTeX
@inproceedings{liu-etal-2025-multimodal-large,
title = "Can Multimodal Large Language Models Understand Spatial Relations?",
author = "Liu, Jingping and
Liu, Ziyan and
Cen, Zhedong and
Zhou, Yan and
Zou, Yinan and
Zhang, Weiyan and
Jiang, Haiyun and
Ruan, Tong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.31/",
doi = "10.18653/v1/2025.acl-long.31",
pages = "620--632",
ISBN = "979-8-89176-251-0"
}