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

arXiv: https://arxiv.org/abs/2508.19967 · HTML: https://mlsanity.com/paper/2508.19967/

## Key facts

- Cited by 2 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 33 references that are in the map.
- First posted on arXiv 27 Aug 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)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [PlaNet - Photo Geolocation with Convolutional Neural Networks](https://mlsanity.com/paper/1602.05314/) (2016)
- [Bridging the Domain Gap for Ground-to-Aerial Image Matching](https://mlsanity.com/paper/1904.11045/) (2019)
- [Revisiting IM2GPS in the Deep Learning Era](https://mlsanity.com/paper/1705.04838/) (2017)
- [Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimation](https://mlsanity.com/paper/2105.07645/) (2021)
- [Correctness Comparison of ChatGPT-4, Gemini, Claude-3, and Copilot for Spatial Tasks](https://mlsanity.com/paper/2401.02404/) (2024)
- [Online Visual Place Recognition via Saliency Re-identification](https://mlsanity.com/paper/2007.14549/) (2020)

## Built on by (most cited first, 2 of 2)

- [City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs](https://mlsanity.com/paper/2512.15933/) (2025)
- [Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?](https://mlsanity.com/paper/2602.05023/) (2026)

## Abstract (arXiv)

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.