Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play

Sha Li, Revanth Gangi Reddy, Khanh Duy Nguyen, Qingyun Wang, Yi Fung, Chi Han, Jiawei Han, Kartik Natarajan, Clare R. Voss, Heng Ji


Abstract
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.
Anthology ID:
2024.emnlp-demo.39
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Delia Irazu Hernandez Farias, Tom Hope, Manling Li
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
372–381
Language:
URL:
https://aclanthology.org/2024.emnlp-demo.39
DOI:
Bibkey:
Cite (ACL):
Sha Li, Revanth Gangi Reddy, Khanh Duy Nguyen, Qingyun Wang, Yi Fung, Chi Han, Jiawei Han, Kartik Natarajan, Clare R. Voss, and Heng Ji. 2024. Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 372–381, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play (Li et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-demo.39.pdf