@inproceedings{suizu-etal-2026-automatic,
title = "Automatic Generation of a Compositional {QA} Benchmark for Geospatial Reasoning under Spatial and Entity Constraints",
author = "Suizu, Tetsuhisa and
Higashiyama, Shohei and
Shindo, Hiroyuki and
Ouchi, Hiroki and
Sakti, Sakriani",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.61/",
pages = "818--830",
ISBN = "979-8-89176-383-8",
abstract = "Despite their recent success, the geospatial reasoning capabilities of large language models (LLMs){---}which require understanding spatial relationships among real-world geo-entities{---}remain underexplored.We propose an automatic method for constructing compositional geographic question answering datasets that jointly consider spatial and entity constraints.The generated dataset serves as a principled benchmark for evaluating how LLMs coordinate spatial computation with entity-level understanding under diverse compositional settings.We evaluate two state-of-the-art LLMs, GPT-5.2 and Gemini 3 Flash, on our dataset. Experimental results show that while the models perform relatively well on questions involving rich entity grounding, their accuracy drops substantially on questions requiring precise quantitative spatial reasoning, such as distance estimation and containment judgment.Our dataset is publicly available for research and reproduction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suizu-etal-2026-automatic">
<titleInfo>
<title>Automatic Generation of a Compositional QA Benchmark for Geospatial Reasoning under Spatial and Entity Constraints</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tetsuhisa</namePart>
<namePart type="family">Suizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohei</namePart>
<namePart type="family">Higashiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroyuki</namePart>
<namePart type="family">Shindo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>Despite their recent success, the geospatial reasoning capabilities of large language models (LLMs)—which require understanding spatial relationships among real-world geo-entities—remain underexplored.We propose an automatic method for constructing compositional geographic question answering datasets that jointly consider spatial and entity constraints.The generated dataset serves as a principled benchmark for evaluating how LLMs coordinate spatial computation with entity-level understanding under diverse compositional settings.We evaluate two state-of-the-art LLMs, GPT-5.2 and Gemini 3 Flash, on our dataset. Experimental results show that while the models perform relatively well on questions involving rich entity grounding, their accuracy drops substantially on questions requiring precise quantitative spatial reasoning, such as distance estimation and containment judgment.Our dataset is publicly available for research and reproduction.</abstract>
<identifier type="citekey">suizu-etal-2026-automatic</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.61/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>818</start>
<end>830</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Generation of a Compositional QA Benchmark for Geospatial Reasoning under Spatial and Entity Constraints
%A Suizu, Tetsuhisa
%A Higashiyama, Shohei
%A Shindo, Hiroyuki
%A Ouchi, Hiroki
%A Sakti, Sakriani
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F suizu-etal-2026-automatic
%X Despite their recent success, the geospatial reasoning capabilities of large language models (LLMs)—which require understanding spatial relationships among real-world geo-entities—remain underexplored.We propose an automatic method for constructing compositional geographic question answering datasets that jointly consider spatial and entity constraints.The generated dataset serves as a principled benchmark for evaluating how LLMs coordinate spatial computation with entity-level understanding under diverse compositional settings.We evaluate two state-of-the-art LLMs, GPT-5.2 and Gemini 3 Flash, on our dataset. Experimental results show that while the models perform relatively well on questions involving rich entity grounding, their accuracy drops substantially on questions requiring precise quantitative spatial reasoning, such as distance estimation and containment judgment.Our dataset is publicly available for research and reproduction.
%U https://aclanthology.org/2026.eacl-srw.61/
%P 818-830
Markdown (Informal)
[Automatic Generation of a Compositional QA Benchmark for Geospatial Reasoning under Spatial and Entity Constraints](https://aclanthology.org/2026.eacl-srw.61/) (Suizu et al., EACL 2026)
ACL