SocialLLM

Overview

This talk surveys challenges and promising directions for using LLMs as social simulators, spanning human behavior prediction, agentic digital twins, multi-agent world simulation, and privacy-preserving synthetic data.

Papers & Case Studies

1. Position: LLM Social Simulations Are a Promising Research Method (Paper)
2. Finetuning LLMs for Human Behavior Prediction in Social Science (Paper)
3. CVS: The Flight Simulator for Management (Case Study)
4. MiroFish (Project)
5. Privasis: Synthesizing the Largest “Public” Private Dataset from Scratch (Paper)

Slides

• Download PDF