Proceedings of the Nineth International Conference on Learning Representations (ICLR 26) · 2026

GeoDiv - Framework for Measuring Geographical Diversity in Text-to-Image Models

Abhipsa Basu, Mohana Singh, Shashank Agnihotri, Margret Keuper, Venkatesh Babu Radhakrishnan

Why this publication matters

A model may generate a narrow stereotype when asked to show everyday life in a particular country. GeoDiv separates different aspects of that problem, including visual variety and socioeconomic portrayal. It gives researchers a more informative way to measure whose experiences are represented in generated images.

Abstract

Text-to-image (T2I) models are rapidly gaining popularity, yet their outputs often lack geographical diversity, reinforce stereotypes, and misrepresent regions. Given their broad reach, it is critical to rigorously evaluate how these models portray the world. Existing diversity metrics either rely on curated datasets or focus on surfacelevel visual similarity, limiting interpretability. We introduce GeoDiv, a framework leveraging large language and vision-language models to assess geographical diversity along two complementary axes: the Socio-Economic Visual Index (SEVI), capturing economic and condition-related cues, and the Visual Diversity Index (VDI), measuring variation in primary entities and backgrounds. Applied to images generated by models such as Stable Diffusion and FLUX.1-dev across 10 entities and 16 countries, GeoDiv reveals a consistent lack of diversity and identifies finegrained attributes where models default to biased portrayals. Strikingly, depictions of countries like India, Nigeria, and Colombia are disproportionately impoverished and worn, reflecting underlying socio-economic biases. These results highlight the need for greater geographical nuance in generative models. GeoDiv provides the first systematic, interpretable framework for measuring such biases, marking a step toward fairer and more inclusive generative systems. Project page: https://abhipsabasu.github.io/geodiv

Abstract source ↗

Figures

Generated images illustrating geographical diversity and socioeconomic portrayal. — **Figure 1.** Lack of Geographical Diversity observed in T2I Generations and the Need for GeoDiv. (a) Text-to-image models produce systematically low visual diversity for the same prompt across countries (example: ‘a photo of a house in Nigeria’), failing to reflect the rich variation seen in real-world images (Ramaswamy et al., 2023). (b) GeoDiv provides an automated, reference-free framework that can quantify such fine-grained geographical differences by evaluating images along four interpretable axes: Entity-Appearance (sloped/flat roof), Background-Appearance (paved/unpaved road), Affluence (luxury/modest settings), and Maintenance (manicured/unkempt). Examples show how the same entity type varies dramatically across countries and generative models. View in source ↗

**Figure 2.** GeoDiv Pipeline. Given an entity e and country c, LLMs generate attribute-based questions specific to e, and a fixed set of background-related questions applicable across entities. A VQA model predicts answer distributions over an image set for both question types, from which GeoDiv computes the Visual Diversity Index (VDI) via normalized Hill number. The VQA model also rates each image on Affluence and Maintenance to compute the Socio-Economic Visual Index (SEVI). View in source ↗

Cite this paper

Download .bib

@inproceedings{basu2026geodivframeworkfor79,
  title = {{GeoDiv - Framework for Measuring Geographical Diversity in Text-to-Image Models}},
  author = {Abhipsa Basu and Mohana Singh and Shashank Agnihotri and Margret Keuper and Venkatesh Babu Radhakrishnan},
  booktitle = {International Conference on Learning Representations},
  year = {2026},
  url = {https://openreview.net/forum?id=WliHWqTfAb}
}

Figures and abstract are reproduced from the linked research sources. Credit remains with the authors and publishers.