Large Language Model-Based Social Simulation
Overview
This field uses language-model agents to model people interacting through networks, institutions, and shared environments, studying outcomes such as opinion change, cooperation, norms, mobility, and policy responses. Common approaches ground agents in surveys, interviews, behavioral histories, or psychological profiles, then combine prompting or fine-tuning with agent-based models, games, memory, and network dynamics. Researchers validate simulations against human surveys, experiments, and real-world traces, measuring both individual response distributions and collective patterns over time. A central challenge is that plausible dialogue or accurate averages do not ensure faithful individual behavior, diverse populations, causal conclusions, or robust results across models and settings.
Latest papers
261 papers53 papers in the last four weeks, up 66% on the four weeks before. 0.3% of all new papers.