# Evaluating Precise Geolocation Inference Capabilities of Vision Language Models

arXiv: https://arxiv.org/abs/2502.14412 · HTML: https://mlsanity.com/paper/2502.14412/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 12 of 12)

- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Beyond Memorization: Violating Privacy Via Inference with Large Language Models](https://mlsanity.com/paper/2310.07298/) (2023)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [A Survey on Benchmarks of Multimodal Large Language Models](https://mlsanity.com/paper/2408.08632/) (2024)
- [PIGEON: Predicting Image Geolocations](https://mlsanity.com/paper/2307.05845/) (2023)
- [Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes](https://mlsanity.com/paper/2303.04249/) (2023)
- [Private Attribute Inference from Images with Vision-Language Models](https://mlsanity.com/paper/2404.10618/) (2024)
- [Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning](https://mlsanity.com/paper/2307.06166/) (2023)
- [LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wild](https://mlsanity.com/paper/2405.20363/) (2024)
- [DeepGeo: Photo Localization with Deep Neural Network](https://mlsanity.com/paper/1810.03077/) (2018)
- [Privacy Concerns Raised by Pervasive User Data Collection From Cyberspace and Their Countermeasures](https://mlsanity.com/paper/2202.04313/) (2022)

## Built on by (most cited first, 12 of 12)

- [GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization](https://mlsanity.com/paper/2505.13731/) (2025)
- [GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning](https://mlsanity.com/paper/2506.00785/) (2025)
- [Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models](https://mlsanity.com/paper/2504.19373/) (2025)
- [GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations](https://mlsanity.com/paper/2508.03209/) (2025)
- [GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2509.04334/) (2025)
- [Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks](https://mlsanity.com/paper/2512.18264/) (2025)
- [Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?](https://mlsanity.com/paper/2602.05023/) (2026)
- [Where Do Images Come From? Analyzing Captions to Geographically Profile Datasets](https://mlsanity.com/paper/2602.09775/) (2026)
- [TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings](https://mlsanity.com/paper/2603.06687/) (2026)
- [GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization](https://mlsanity.com/paper/2603.24376/) (2026)
- [GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation](https://mlsanity.com/paper/2608.29483/) (2026)
- [Hiding in Plain Sight: A Diffusion-based Mitigation of Geolocation Privacy Leakage in Vision-Language Models](https://mlsanity.com/paper/2609.21363/) (2026)

## Abstract (arXiv)

The prevalence of Vision-Language Models (VLMs) raises important questions about privacy in an era where visual information is increasingly available. While foundation VLMs demonstrate broad knowledge and learned capabilities, we specifically investigate their ability to infer geographic location from previously unseen image data. This paper introduces a benchmark dataset collected from Google Street View that represents its global distribution of coverage. Foundation models are evaluated on single-image geolocation inference, with many achieving median distance errors of <300 km. We further evaluate VLM "agents" with access to supplemental tools, observing up to a 30.6% decrease in distance error. Our findings establish that modern foundation VLMs can act as powerful image geolocation tools, without being specifically trained for this task. When coupled with increasing accessibility of these models, our findings have greater implications for online privacy. We discuss these risks, as well as future work in this area.