@inproceedings{premsri-kordjamshidi-2025-forest,
title = "{F}o{REST}: Frame of Reference Evaluation in Spatial Reasoning Tasks",
author = "Premsri, Tanawan and
Kordjamshidi, Parisa",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1772/",
pages = "34965--34991",
ISBN = "979-8-89176-332-6",
abstract = "Spatial reasoning is a fundamental aspect of human intelligence. One key concept in spatial cognition is the Frame of Reference (FoR), which identifies the perspective of spatial expressions. Despite its significance, FoR has received limited attention in AI models that need spatial intelligence. There is a lack of dedicated benchmarks and in-depth evaluation of large language models (LLMs) in this area. To address this issue, we introduce the Frame of Reference Evaluation in Spatial Reasoning Tasks (FoREST) benchmark, designed to assess FoR comprehension in LLMs. We evaluate LLMs on answering questions that require FoR comprehension and layout generation in text-to-image models using FoREST. Our results reveal a notable performance gap across different FoR classes in various LLMs, affecting their ability to generate accurate layouts for text-to-image generation. This highlights critical shortcomings in FoR comprehension. To improve FoR understanding, we propose Spatial-Guided prompting, which improves LLMs' ability to extract essential spatial concepts. Our proposed method improves overall performance across spatial reasoning tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="premsri-kordjamshidi-2025-forest">
<titleInfo>
<title>FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanawan</namePart>
<namePart type="family">Premsri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parisa</namePart>
<namePart type="family">Kordjamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Spatial reasoning is a fundamental aspect of human intelligence. One key concept in spatial cognition is the Frame of Reference (FoR), which identifies the perspective of spatial expressions. Despite its significance, FoR has received limited attention in AI models that need spatial intelligence. There is a lack of dedicated benchmarks and in-depth evaluation of large language models (LLMs) in this area. To address this issue, we introduce the Frame of Reference Evaluation in Spatial Reasoning Tasks (FoREST) benchmark, designed to assess FoR comprehension in LLMs. We evaluate LLMs on answering questions that require FoR comprehension and layout generation in text-to-image models using FoREST. Our results reveal a notable performance gap across different FoR classes in various LLMs, affecting their ability to generate accurate layouts for text-to-image generation. This highlights critical shortcomings in FoR comprehension. To improve FoR understanding, we propose Spatial-Guided prompting, which improves LLMs’ ability to extract essential spatial concepts. Our proposed method improves overall performance across spatial reasoning tasks.</abstract>
<identifier type="citekey">premsri-kordjamshidi-2025-forest</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1772/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>34965</start>
<end>34991</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks
%A Premsri, Tanawan
%A Kordjamshidi, Parisa
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F premsri-kordjamshidi-2025-forest
%X Spatial reasoning is a fundamental aspect of human intelligence. One key concept in spatial cognition is the Frame of Reference (FoR), which identifies the perspective of spatial expressions. Despite its significance, FoR has received limited attention in AI models that need spatial intelligence. There is a lack of dedicated benchmarks and in-depth evaluation of large language models (LLMs) in this area. To address this issue, we introduce the Frame of Reference Evaluation in Spatial Reasoning Tasks (FoREST) benchmark, designed to assess FoR comprehension in LLMs. We evaluate LLMs on answering questions that require FoR comprehension and layout generation in text-to-image models using FoREST. Our results reveal a notable performance gap across different FoR classes in various LLMs, affecting their ability to generate accurate layouts for text-to-image generation. This highlights critical shortcomings in FoR comprehension. To improve FoR understanding, we propose Spatial-Guided prompting, which improves LLMs’ ability to extract essential spatial concepts. Our proposed method improves overall performance across spatial reasoning tasks.
%U https://aclanthology.org/2025.emnlp-main.1772/
%P 34965-34991
Markdown (Informal)
[FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks](https://aclanthology.org/2025.emnlp-main.1772/) (Premsri & Kordjamshidi, EMNLP 2025)
ACL