<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-pixels-places">
    <titleInfo>
        <title>From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lingyao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Runlong</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qikai</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bowei</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min</namePart>
        <namePart type="family">Deng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaowei</namePart>
        <namePart type="family">Jia</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Image geolocalization is important for applications in crisis response, digital forensics, and location-based intelligence. While recent advances in large language models (LLMs) offer new opportunities for visual reasoning, their ability to perform image geolocalization remains underexplored. In this study, we introduce a benchmark called IMAGEO-Bench that systematically evaluates accuracy, distance error, geospatial bias, and reasoning process. Through experiments on 10 state-of-the-art LLMs, we reveal clear performance disparities, with closed-source models generally showing stronger reasoning. Importantly, we uncover systematic geospatial disparities: LLMs perform better in high-resource regions (e.g., North America, Western Europe, and California) while exhibiting degraded performance in underrepresented areas. Regression diagnostics demonstrate that successful geolocalization is strongly associated with recognizing urban settings, outdoor environments, street-level imagery, and identifiable landmarks. Overall, IMAGEO-Bench provides a rigorous lens into the spatial reasoning capabilities of LLMs and offers implications for building geolocation-aware AI systems.</abstract>
    <identifier type="citekey">li-etal-2026-pixels-places</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1818/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>41432</start>
            <end>41457</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models
%A Li, Lingyao
%A Yu, Runlong
%A Hu, Qikai
%A Li, Bowei
%A Deng, Min
%A Zhou, Yang
%A Jia, Xiaowei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F li-etal-2026-pixels-places
%X Image geolocalization is important for applications in crisis response, digital forensics, and location-based intelligence. While recent advances in large language models (LLMs) offer new opportunities for visual reasoning, their ability to perform image geolocalization remains underexplored. In this study, we introduce a benchmark called IMAGEO-Bench that systematically evaluates accuracy, distance error, geospatial bias, and reasoning process. Through experiments on 10 state-of-the-art LLMs, we reveal clear performance disparities, with closed-source models generally showing stronger reasoning. Importantly, we uncover systematic geospatial disparities: LLMs perform better in high-resource regions (e.g., North America, Western Europe, and California) while exhibiting degraded performance in underrepresented areas. Regression diagnostics demonstrate that successful geolocalization is strongly associated with recognizing urban settings, outdoor environments, street-level imagery, and identifiable landmarks. Overall, IMAGEO-Bench provides a rigorous lens into the spatial reasoning capabilities of LLMs and offers implications for building geolocation-aware AI systems.
%U https://aclanthology.org/2026.emnlp-main.1818/
%P 41432-41457

Markdown (Informal)

[From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models](https://aclanthology.org/2026.emnlp-main.1818/) (Li et al., EMNLP 2026)

• From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models (Li et al., EMNLP 2026)

ACL

• Lingyao Li, Runlong Yu, Qikai Hu, Bowei Li, Min Deng, Yang Zhou, and Xiaowei Jia. 2026. From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 41432–41457, Budapest, Hungary. Association for Computational Linguistics.