发表机构
University of Central Florida; Case Western Reserve University（中佛罗里达大学; 凯斯西储大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GeoOutageBench是一个新基准，用于评估大语言模型在多模态停电与韧性分析中的地理时空知识图谱问答，涵盖模糊问题理解、本体效用和答案准确性，并提供了设计原则和开源资源。
AI 中文摘要
我们引入了GeoOutageBench，一个用于评估基于大语言模型的地理时空知识图谱问答（KGQA）在多模态停电与韧性分析中的基准。与现有的面向网络知识的KGQA基准不同，GeoOutageBench考虑了一个时空知识图谱，该图谱整合了来自停电记录、遥感、天气观测、风暴和电力事件、地理实体以及领域本体的视觉、文本和结构化数据。它提供了一个能力查询分类法，涵盖不同难度级别，从时空包含和邻近性、时空共现分析、多模态证据到假设性评估。在多模态知识图谱和查询类别上，GeoOutageBench提供了对三个重要、高度连贯但研究较少任务的用户可配置评估：（1）大语言模型在自然语言到SPARQL解释方面对模糊地理时空问题的理解，（2）基于查询的本体效用评估，以及（3）多模态KGQA检索的答案准确性。GeoOutageBench为评估支持现实世界基础设施韧性分析的LLM-KG系统提供了设计原则和基础。我们的基准、源代码、数据、结果和其他文档可在该https URL获取。
英文摘要
We introduce GeoOutageBench, a benchmark for assessing LLM-based geospatiotemporal KGQA for multimodal outage and resilience analysis. Unlike existing KGQA benchmarks for Web knowledge, GeoOutageBench considers a spatiotemporal KG that integrates visual, textual, and structured data from outage records, remote sensing, weather observations, storm and power events, geographic entities, and domain ontologies. It provides a competency query taxonomy at different difficulty levels from spatiotemporal containment and proximity, spatiotemporal co-occurrence analysis, multimodal evidence, to hypothetical evaluation. Over multimodal KG and query classes, GeoOutageBench provides user-configurable evaluation of three important, highly coherent yet less studied tasks: (1) LLMs' understanding for ambiguous geospatiotemporal questions in terms of NL to SPARQL interpretation, (2) query-driven assessment of ontology utility, and (3) answer accuracy of multimodal KGQA retrieval. GeoOutageBench provides a design principle and foundation for assessing LLM-KG systems that support real-world infrastructure resilience analysis. Our benchmark, source code, data, results, and other documentation are available at https://github.com/UCF-SAGE/GeoOutageBench.
Comments13 pages, 6 figures, 7 tables. Accepted to the 34th ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL '26), November 3-6, 2026, Riverside, CA, USA
