SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation
By: Xuhui Zhou , Zhe Su , Sophie Feng and more
Potential Business Impact:
Builds fake worlds to test social ideas.
Social simulation through large language model (LLM) agents is a promising approach to explore and validate hypotheses related to social science questions and LLM agents behavior. We present SOTOPIA-S4, a fast, flexible, and scalable social simulation system that addresses the technical barriers of current frameworks while enabling practitioners to generate multi-turn and multi-party LLM-based interactions with customizable evaluation metrics for hypothesis testing. SOTOPIA-S4 comes as a pip package that contains a simulation engine, an API server with flexible RESTful APIs for simulation management, and a web interface that enables both technical and non-technical users to design, run, and analyze simulations without programming. We demonstrate the usefulness of SOTOPIA-S4 with two use cases involving dyadic hiring negotiation and multi-party planning scenarios.
Similar Papers
LIFELONG SOTOPIA: Evaluating Social Intelligence of Language Agents Over Lifelong Social Interactions
Artificial Intelligence
AI learns to be social like people.
SOCIA: An End-to-End Agentic Framework for Automated Cyber-Physical-Social Simulator Generation
Artificial Intelligence
Builds fake worlds to test how people and tech interact.
Social World Models
Artificial Intelligence
Helps AI understand people's feelings and actions.