# Exploring Spatial Language Grounding Through Referring Expressions

arXiv: https://arxiv.org/abs/2502.04359 · HTML: https://mlsanity.com/paper/2502.04359/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- First posted on arXiv 4 Feb 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Built on by (most cited first, 3 of 3)

- [Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation](https://mlsanity.com/paper/2504.16060/) (2025)
- [Multi-label Instance-level Generalised Visual Grounding in Agriculture](https://mlsanity.com/paper/2603.06699/) (2026)
- [Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding](https://mlsanity.com/paper/2512.06769/) (2025)

## Abstract (arXiv)

Spatial Reasoning is an important component of human cognition and is an area in which the latest Vision-language models (VLMs) show signs of difficulty. The current analysis works use image captioning tasks and visual question answering. In this work, we propose using the Referring Expression Comprehension task instead as a platform for the evaluation of spatial reasoning by VLMs. This platform provides the opportunity for a deeper analysis of spatial comprehension and grounding abilities when there is 1) ambiguity in object detection, 2) complex spatial expressions with a longer sentence structure and multiple spatial relations, and 3) expressions with negation ('not'). In our analysis, we use task-specific architectures as well as large VLMs and highlight their strengths and weaknesses in dealing with these specific situations. While all these models face challenges with the task at hand, the relative behaviors depend on the underlying models and the specific categories of spatial semantics (topological, directional, proximal, etc.). Our results highlight these challenges and behaviors and provide insight into research gaps and future directions.