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

Documentdetail

ID kaart

oai:arXiv.org:2410.18935

Onderwerp

Computer Science - Artificial Inte... Computer Science - Computation and...

Auteur

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

Categorie

Computer Science

Jaar

2024

vermelding datum

30-10-2024

Trefwoorden

cultural complex events

Metriek

Beschrijving

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.

;Comment: Accepted as EMNLP 2024 Demo

Li, Sha,Reddy, Revanth Gangi,Nguyen, Khanh Duy,Wang, Qingyun,Fung, May,Han, Chi,Han, Jiawei,Natarajan, Kartik,Voss, Clare R.,Ji, Heng, 2024, Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play