@inproceedings{wang-etal-2025-ai,
title = "{AI} Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with {K}orea{GEO}",
author = "Wang, Xiaonan and
Shao, Bo and
Kim, Hansaem",
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.501/",
doi = "10.18653/v1/2025.emnlp-main.501",
pages = "9886--9903",
ISBN = "979-8-89176-332-6",
abstract = "Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risks in everyday social media posts. Yet, a systematic evaluation of such risks is still lacking: existing benchmarks show coarse granularity, linguistic bias, and a neglect of multimodal privacy risks. To address these gaps, we introduce KoreaGEO, the first fine-grained, multimodal, and privacy-aware benchmark for geolocation, built on Korean street views. The benchmark covers four socio-spatial clusters and nine place types with rich contextual annotations and two captioning styles that simulate real-world privacy exposure. To evaluate mainstream VLMs, we design a three-path protocol spanning image-only, functional-caption, and high-risk-caption inputs, enabling systematic analysis of localization accuracy, spatial bias, and reasoning behavior. Results show that input modality exerts a stronger influence on localization precision and privacy exposure than model scale or architecture, with high-risk captions substantially boosting accuracy. Moreover, they highlight structural prediction biases toward core cities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-ai">
<titleInfo>
<title>AI Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with KoreaGEO</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaonan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</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>Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risks in everyday social media posts. Yet, a systematic evaluation of such risks is still lacking: existing benchmarks show coarse granularity, linguistic bias, and a neglect of multimodal privacy risks. To address these gaps, we introduce KoreaGEO, the first fine-grained, multimodal, and privacy-aware benchmark for geolocation, built on Korean street views. The benchmark covers four socio-spatial clusters and nine place types with rich contextual annotations and two captioning styles that simulate real-world privacy exposure. To evaluate mainstream VLMs, we design a three-path protocol spanning image-only, functional-caption, and high-risk-caption inputs, enabling systematic analysis of localization accuracy, spatial bias, and reasoning behavior. Results show that input modality exerts a stronger influence on localization precision and privacy exposure than model scale or architecture, with high-risk captions substantially boosting accuracy. Moreover, they highlight structural prediction biases toward core cities.</abstract>
<identifier type="citekey">wang-etal-2025-ai</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.501</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.501/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>9886</start>
<end>9903</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AI Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with KoreaGEO
%A Wang, Xiaonan
%A Shao, Bo
%A Kim, Hansaem
%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 wang-etal-2025-ai
%X Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risks in everyday social media posts. Yet, a systematic evaluation of such risks is still lacking: existing benchmarks show coarse granularity, linguistic bias, and a neglect of multimodal privacy risks. To address these gaps, we introduce KoreaGEO, the first fine-grained, multimodal, and privacy-aware benchmark for geolocation, built on Korean street views. The benchmark covers four socio-spatial clusters and nine place types with rich contextual annotations and two captioning styles that simulate real-world privacy exposure. To evaluate mainstream VLMs, we design a three-path protocol spanning image-only, functional-caption, and high-risk-caption inputs, enabling systematic analysis of localization accuracy, spatial bias, and reasoning behavior. Results show that input modality exerts a stronger influence on localization precision and privacy exposure than model scale or architecture, with high-risk captions substantially boosting accuracy. Moreover, they highlight structural prediction biases toward core cities.
%R 10.18653/v1/2025.emnlp-main.501
%U https://aclanthology.org/2025.emnlp-main.501/
%U https://doi.org/10.18653/v1/2025.emnlp-main.501
%P 9886-9903
Markdown (Informal)
[AI Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with KoreaGEO](https://aclanthology.org/2025.emnlp-main.501/) (Wang et al., EMNLP 2025)
ACL