@inproceedings{zhang-2026-route,
title = "From Route to Survey: Probing Spatial Perspective Transformation in Large Language Models",
author = "Zhang, Haotong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1011/",
doi = "10.18653/2026.findings-emnlp.1011",
pages = "21368--21386",
ISBN = "979-8-89176-462-0",
abstract = "Spatial perspective transformation is a fundamental component of human spatial cognition, yet it remains unclear whether large language models (LLMs) can exhibit robust spatial reasoning abilities that support such transformations. We introduce a controlled dataset inspired by cognitive science studies, combining route-view and survey-view descriptions across multiple environmental topologies. Experiments on both open-source and closed-source LLMs show that models readily learn within-perspective reasoning but continue to struggle with cross-perspective transformation, especially from route-view to survey-view reasoning. The learnt capabilities remain strongly topology-dependent and generalise asymmetrically between within-perspective and cross-perspective settings. Scaling substantially improves allocentric and within-perspective reasoning, but does not uniformly resolve cross-perspective transformation difficulty, while chain-of-thought prompting provides little benefit. Overall, our results suggest that current LLMs do not consistently demonstrate perspective-invariant spatial reasoning across perspectives and environments. Code and datasets are available at https://github.com/zhanghaotong1/EMNLP-2026-perspective-transformation-in-LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-2026-route">
<titleInfo>
<title>From Route to Survey: Probing Spatial Perspective Transformation in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haotong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Spatial perspective transformation is a fundamental component of human spatial cognition, yet it remains unclear whether large language models (LLMs) can exhibit robust spatial reasoning abilities that support such transformations. We introduce a controlled dataset inspired by cognitive science studies, combining route-view and survey-view descriptions across multiple environmental topologies. Experiments on both open-source and closed-source LLMs show that models readily learn within-perspective reasoning but continue to struggle with cross-perspective transformation, especially from route-view to survey-view reasoning. The learnt capabilities remain strongly topology-dependent and generalise asymmetrically between within-perspective and cross-perspective settings. Scaling substantially improves allocentric and within-perspective reasoning, but does not uniformly resolve cross-perspective transformation difficulty, while chain-of-thought prompting provides little benefit. Overall, our results suggest that current LLMs do not consistently demonstrate perspective-invariant spatial reasoning across perspectives and environments. Code and datasets are available at https://github.com/zhanghaotong1/EMNLP-2026-perspective-transformation-in-LLMs.</abstract>
<identifier type="citekey">zhang-2026-route</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1011</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1011/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>21368</start>
<end>21386</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Route to Survey: Probing Spatial Perspective Transformation in Large Language Models
%A Zhang, Haotong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zhang-2026-route
%X Spatial perspective transformation is a fundamental component of human spatial cognition, yet it remains unclear whether large language models (LLMs) can exhibit robust spatial reasoning abilities that support such transformations. We introduce a controlled dataset inspired by cognitive science studies, combining route-view and survey-view descriptions across multiple environmental topologies. Experiments on both open-source and closed-source LLMs show that models readily learn within-perspective reasoning but continue to struggle with cross-perspective transformation, especially from route-view to survey-view reasoning. The learnt capabilities remain strongly topology-dependent and generalise asymmetrically between within-perspective and cross-perspective settings. Scaling substantially improves allocentric and within-perspective reasoning, but does not uniformly resolve cross-perspective transformation difficulty, while chain-of-thought prompting provides little benefit. Overall, our results suggest that current LLMs do not consistently demonstrate perspective-invariant spatial reasoning across perspectives and environments. Code and datasets are available at https://github.com/zhanghaotong1/EMNLP-2026-perspective-transformation-in-LLMs.
%R 10.18653/2026.findings-emnlp.1011
%U https://aclanthology.org/2026.findings-emnlp.1011/
%U https://doi.org/10.18653/2026.findings-emnlp.1011
%P 21368-21386
Markdown (Informal)
[From Route to Survey: Probing Spatial Perspective Transformation in Large Language Models](https://aclanthology.org/2026.findings-emnlp.1011/) (Zhang, Findings 2026)
ACL