SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation
This provides a user-friendly tool for practitioners in social science and AI to conduct large-scale simulations without programming, though it is incremental as it builds on existing LLM-based simulation approaches.
The authors tackled the problem of technical barriers in social simulation frameworks by developing SOTOPIA-S4, a fast, flexible, and scalable system that enables users to generate multi-turn and multi-party LLM-based interactions with customizable evaluation metrics, demonstrated through use cases like dyadic hiring negotiation and multi-party planning.
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.