地图仍能提升大模型地理理解能力，尤其配合数据时效果更佳。
Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation Model Spatial Understanding
- 构建2400张合成地图的基准测试，评估模型对地图与地理数据的处理能力。
- 结合地图和数据时，模型在空间推理任务中准确率显著提升。
- 适合研究大模型地理认知、地图可视化或空间智能的开发者与学者。
空间理解对基础模型至关重要，地图长期以来帮助人类组织和推理地理信息。本研究探讨当模型可直接处理结构化地理数据时，分级统计图（choropleth maps）是否仍对机器的空间理解有帮助。我们提出ChoroplethMap-Bench基准，包含2,400张合成分级地图、对应的GeoJSON数据及12,000个问题，覆盖五类认知维度：识别、空间识别、比较、排序与划定。在三种输入条件下（仅数据、仅地图、数据+地图）评估22个开源与专有模型。结果表明，地图显著提升空间推理表现，尤其在结合符号数据且需高层次空间模式理解的任务中。进一步分析了地图类型、颜色色相、空间结构、提示策略、语言、地理上下文、解码设置、分类方法与响应稳定性的影响。总体而言，数据+地图条件表现最优，证明地图仍是基础模型空间推理中具有价值的外部表征。
原文摘要 · Abstract (English)
Spatial understanding is crucial for foundation models (FMs), and maps have long helped humans organize and reason about geographic information. This study examines whether choropleth maps remain useful for machine spatial understanding when models can directly process structured geodata. We introduce ChoroplethMap-Bench, a controlled benchmark containing 2,400 synthetic choropleth maps, corresponding GeoJSON data, and 12,000 questions across five cognitive dimensions: Identify, Spatial Recognition, Compare, Rank, and Delineate. We evaluate 22 open-source and proprietary models under three input conditions: Data Only, Map Only, and Data + Map. The results show that maps substantially improve spatial reasoning, especially when combined with symbolic data and for tasks requiring higher-level understanding of spatial patterns. We further analyze the effects of map type, color hue, and spatial structure, as well as prompting strategies, language, geographic context, decoding settings, classification methods, and response stability. Overall, the Data + Map condition achieves the strongest performance, demonstrating that maps remain valuable external representations for foundation model spatial reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。