发表机构
National University of Singapore; Shandong University of Science and Technology; University of Oxford（新加坡国立大学; 山东科技大学; 牛津大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对视觉语言模型地理定位易受地标偏差影响的问题，提出证据驱动推理框架HoloGeo，借助高质量数据集，通过多维度奖励实现平衡关注与联合推理，经实验验证其在多个数据集上能有效减轻地标偏差，提升地理定位性能。
AI 中文摘要
视觉语言模型（VLMs）的进展改善了图像地理定位，但现有模型仍易受地标偏差影响，导致忽视地理线索或形成虚假关联，造成定位不准确。为此设计了偏差强度（BI）和偏差危害（BH）两个量化指标，建立了LandmarkBias - 3K基准。提出证据驱动推理框架HoloGeo，借助高质量BF - 30k数据集，通过纳入多维度奖励鼓励对多样视觉线索的平衡关注，实现证据驱动联合推理。实验表明HoloGeo在多个数据集上表现出色，验证了其对稳健地理空间推理的有效性。
英文摘要
Recent advances in Vision-Language Models (VLMs) have significantly improved image geo-localization, yet existing models remain susceptible to landmark bias, causing them to overlook geographical cues or form spurious correlations, ultimately resulting in inaccurate localization. To systematically investigate this issue, we first design two quantitative metrics, Bias Intensity (BI) and Bias Harmfulness (BH), to characterize the impact of landmarks exerted on model reasoning, and establish a comprehensive benchmark, LandmarkBias-3K. To mitigate landmark bias, we further propose an evidence-driven reasoning framework, HoloGeo, to improve the reliability of geo-localization. HoloGeo is supported by a high-quality dataset, BF-30k, annotated with structured multi-evidence bias-free reasoning chains. By incorporating multi-dimensional rewards, HoloGeo explicitly encourages balanced attention over diverse visual cues and achieves evidence-driven joint reasoning. Extensive experiments demonstrate that HoloGeo not only maintains excellent performance on IM2GPS3K and YFCC4k but also significantly outperforms existing open-source VLMs on LandmarkBias-3K, validating its effectiveness for robust geospatial reasoning.
