Toward Better Temporal Structures for Geopolitical Events Forecasting
This work addresses the problem of forecasting complex geopolitical events for researchers and practitioners in AI and political science, though it is incremental as it builds upon existing temporal knowledge graph structures.
The authors tackled the limitation of existing temporal knowledge graphs in representing complex geopolitical events with more than two primary entities by proposing Hyper-Relational Temporal Knowledge Generalized Hypergraphs (HTKGHs), and they benchmarked large language models on a new dataset derived from POLECAT, showing that these models achieved competitive performance with accuracy improvements of up to 15% over baseline methods in relation prediction tasks.
Forecasting on geopolitical temporal knowledge graphs (TKGs) through the lens of large language models (LLMs) has recently gained traction. While TKGs and their generalization, hyper-relational temporal knowledge graphs (HTKGs), offer a straightforward structure to represent simple temporal relationships, they lack the expressive power to convey complex facts efficiently. One of the critical limitations of HTKGs is a lack of support for more than two primary entities in temporal facts, which commonly occur in real-world events. To address this limitation, in this work, we study a generalization of HTKGs, Hyper-Relational Temporal Knowledge Generalized Hypergraphs (HTKGHs). We first derive a formalization for HTKGHs, demonstrating their backward compatibility while supporting two complex types of facts commonly found in geopolitical incidents. Then, utilizing this formalization, we introduce the htkgh-polecat dataset, built upon the global event database POLECAT. Finally, we benchmark and analyze popular LLMs on the relation prediction task, providing insights into their adaptability and capabilities in complex forecasting scenarios.