Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play
This addresses the need for better preparedness in government and society by simulating nuanced events, though it is incremental as it builds on existing agent-based and schema-guided methods.
The paper tackles the problem of simulating complex news events like natural disasters and socio-political conflicts by developing a controllable simulator guided by event schemas and cultural norms, resulting in higher coherence and appropriateness as favored by humanitarian assistance participants.
Complex news events, such as natural disasters and socio-political conflicts, require swift responses from the government and society. Relying on historical events to project the future is insufficient as such events are sparse and do not cover all possible conditions and nuanced situations. Simulation of these complex events can help better prepare and reduce the negative impact. We develop a controllable complex news event simulator guided by both the event schema representing domain knowledge about the scenario and user-provided assumptions representing case-specific conditions. As event dynamics depend on the fine-grained social and cultural context, we further introduce a geo-diverse commonsense and cultural norm-aware knowledge enhancement component. To enhance the coherence of the simulation, apart from the global timeline of events, we take an agent-based approach to simulate the individual character states, plans, and actions. By incorporating the schema and cultural norms, our generated simulations achieve much higher coherence and appropriateness and are received favorably by participants from a humanitarian assistance organization.