An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

Fatemeh Shiri, Xiao-Yu Guo, Mona Golestan Far, Xin Yu, Reza Haf, Yuan-Fang Li


Abstract
Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs’ spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs’ spatial reasoning. Secondly, LMMs struggle more with questions posed from the human perspective than the camera perspective about the image. Thirdly, chain of thought (CoT) prompting does not improve model performance on complex multi-hop questions involving spatial relations. Moreover, spatial reasoning steps are much less accurate than non-spatial ones across MLLMs. Lastly, our perturbation analysis on GQA-spatial reveals that LMMs are much stronger at basic object detection than complex spatial reasoning. We believe our new benchmark dataset and in-depth analyses can spark further research on LMMs spatial reasoning.
Anthology ID:
2024.emnlp-main.1195
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
21440–21455
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1195
DOI:
10.18653/v1/2024.emnlp-main.1195
Bibkey:
Cite (ACL):
Fatemeh Shiri, Xiao-Yu Guo, Mona Golestan Far, Xin Yu, Reza Haf, and Yuan-Fang Li. 2024. An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21440–21455, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models (Shiri et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1195.pdf