Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grainge, Oliver, Waheed, Sania, Stilgoe, Jack, Milford, Michael, Ehsan, Shoaib
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915466438508544
author Grainge, Oliver
Waheed, Sania
Stilgoe, Jack
Milford, Michael
Ehsan, Shoaib
author_facet Grainge, Oliver
Waheed, Sania
Stilgoe, Jack
Milford, Michael
Ehsan, Shoaib
contents Geo-localization is the task of identifying the location of an image using visual cues alone. It has beneficial applications, such as improving disaster response, enhancing navigation, and geography education. Recently, Vision-Language Models (VLMs) are increasingly demonstrating capabilities as accurate image geo-locators. This brings significant privacy risks, including those related to stalking and surveillance, considering the widespread uses of AI models and sharing of photos on social media. The precision of these models is likely to improve in the future. Despite these risks, there is little work on systematically evaluating the geolocation precision of Generative VLMs, their limits and potential for unintended inferences. To bridge this gap, we conduct a comprehensive assessment of the geolocation capabilities of 25 state-of-the-art VLMs on four benchmark image datasets captured in diverse environments. Our results offer insight into the internal reasoning of VLMs and highlight their strengths, limitations, and potential societal risks. Our findings indicate that current VLMs perform poorly on generic street-level images yet achieve notably high accuracy (61\%) on images resembling social media content, raising significant and urgent privacy concerns.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19967
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models
Grainge, Oliver
Waheed, Sania
Stilgoe, Jack
Milford, Michael
Ehsan, Shoaib
Computer Vision and Pattern Recognition
Geo-localization is the task of identifying the location of an image using visual cues alone. It has beneficial applications, such as improving disaster response, enhancing navigation, and geography education. Recently, Vision-Language Models (VLMs) are increasingly demonstrating capabilities as accurate image geo-locators. This brings significant privacy risks, including those related to stalking and surveillance, considering the widespread uses of AI models and sharing of photos on social media. The precision of these models is likely to improve in the future. Despite these risks, there is little work on systematically evaluating the geolocation precision of Generative VLMs, their limits and potential for unintended inferences. To bridge this gap, we conduct a comprehensive assessment of the geolocation capabilities of 25 state-of-the-art VLMs on four benchmark image datasets captured in diverse environments. Our results offer insight into the internal reasoning of VLMs and highlight their strengths, limitations, and potential societal risks. Our findings indicate that current VLMs perform poorly on generic street-level images yet achieve notably high accuracy (61\%) on images resembling social media content, raising significant and urgent privacy concerns.
title Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.19967