LLM Agents for Georelating - A New Task for Locating Events
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Standard
Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems. New York, NY, USA: Association for Computing Machinery, 2025. S. 277–280 (SIGSPATIAL '25).
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - LLM Agents for Georelating - A New Task for Locating Events
AU - Moltzen, Kai
AU - Huang, Junbo
AU - Usbeck, Ricardo
PY - 2025/12/12
Y1 - 2025/12/12
N2 - Accurately identifying disaster-affected areas is crucial for data-driven disaster resilience. In response, we introduce Georelating, a task that infers affected areas from textual reports containing complex locative expressions, moving beyond traditional geoparsing approaches that rely on explicit point locations. Georelating instead combines resolving unnamed regions and reasoning about spatial relations to represent event-affected areas within standardized Discrete Global Grid Systems (DGGSs).We propose addressing Georelating with a pipeline capitalizing on the contextual understanding of large language model (LLM) agents to perform geospatial reasoning. Preliminary evaluation highlights the potential of this approach for the foundational geocoding stage and the novel Georelating task. We point out future paths for enhancing Georelating systems toward intuitive and efficient disaster information systems.
AB - Accurately identifying disaster-affected areas is crucial for data-driven disaster resilience. In response, we introduce Georelating, a task that infers affected areas from textual reports containing complex locative expressions, moving beyond traditional geoparsing approaches that rely on explicit point locations. Georelating instead combines resolving unnamed regions and reasoning about spatial relations to represent event-affected areas within standardized Discrete Global Grid Systems (DGGSs).We propose addressing Georelating with a pipeline capitalizing on the contextual understanding of large language model (LLM) agents to perform geospatial reasoning. Preliminary evaluation highlights the potential of this approach for the foundational geocoding stage and the novel Georelating task. We point out future paths for enhancing Georelating systems toward intuitive and efficient disaster information systems.
KW - georelating
KW - reflective language agents
KW - spatial reasoning
KW - DGGS
U2 - 10.1145/3748636.3762733
DO - 10.1145/3748636.3762733
M3 - Article in conference proceedings
SN - 9798400720864
T3 - SIGSPATIAL '25
SP - 277
EP - 280
BT - Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems
PB - Association for Computing Machinery
CY - New York, NY, USA
ER -