Evaluation of Multilingual Ability to Use Spatial Deictic Expressions in Vision-Language Models
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
One of the expected abilities of vision-language models (VLMs) is spatial reasoning ability based on a given text and image. To evaluate the spatial reasoning abilities of VLMs, we focus on the use of spatial deictic expressions, which are defined as spatial expressions whose referent is determined by their situational context, such as ``this'' and ``that''. To handle spatial deictic expressions, VLMs must jointly reason over language and visual space, grounding context-dependent references in the image's spatial structure. In addition, selecting appropriate spatial deictic expressions across languages requires VLMs to understand the language-specific spatial distinctions encoded by these expressions. In this paper, we develop a benchmark to evaluate the multilingual ability of VLMs to use spatial deictic expressions in four languages. Our experiments using this benchmark reveal that the tested models use demonstratives in a manner different from that of humans, particularly in selecting the appropriate demonstratives based on the distance to the object.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 8 of its 18 references that are in the map. First posted on arXiv 8 Jul 2026.
Builds on
8 of 18 references.
Closest ancestors · 2
Same direction, newest first
- 2025Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods14 Nov
- 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces18 Dec
Other references · 6
- 2024PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilitiescited by 59
- 2024Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguitiescited by 59
- 2024SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluationcited by 31
- 2024A Deixis-Centered Approach for Documenting Remote Synchronous Communication around Data Visualizationscited by 5
- 2025Vision language models are unreliable at trivial spatial cognitioncited by 4
- 2025PISA-Bench: The PISA Index as a Multilingual and Multimodal Metric for the Evaluation of Vision-Language Modelscited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models
- 2025Referring Expressions as a Lens into Spatial Language Grounding in Vision-Language Models
- 2024Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
- 2025Exploring Spatial Language Grounding Through Referring Expressions
- 2022Visual Spatial Reasoning
- 2023What's "up" with vision-language models? Investigating their struggle with spatial reasoning
- 2024Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
- 2025InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models