We expose a significant popularity bias in state-of-the-art vision-language models (VLMs), which achieve up to 34% higher accuracy on famous buildings compared to ordinary ones, indicating a reliance on memorization over generalizable understanding. To systematically investigate this, we introduce the largest open benchmark for this task: the YearGuessr dataset, a collection of 55,546 building images with multi-modal attributes from 157 countries, annotated with continuous ordinal labels of their construction year (1001-2024), GPS data, and page-view counts as a proxy for popularity. Using this dataset, we frame the construction year prediction task as ordinal regression and introduce popularity-aware interval accuracy metrics to quantify this bias. Our resulting benchmark of 30+ models, including our YearCLIP model, confirms that VLMs excel on popular, memorized items but struggle significantly with unrecognized subjects, exposing a critical flaw in their reasoning capabilities. Project page: https://sytwu.github.io/BeyondMemo/
Cite
@article{arxiv.2512.21337,
title = {Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models},
author = {Li-Zhong Szu-Tu and Ting-Lin Wu and Chia-Jui Chang and He Syu and Yu-Lun Liu},
journal= {arXiv preprint arXiv:2512.21337},
year = {2025}
}