Toward Better Temporal Structures for Geopolitical Events Forecasting

ArXi:2601.00430v2 Announce Type: replace 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 for than two primary entities in temporal facts, which commonly occur in real-world events.