From Individual to Society: Social Simulation Driven by LLM-based Agent
Monday, January 20, 2025
Simulating human social behavior is a complex task involving principles and techniques from multiple disciplines. Traditional approaches use Agent-Based Models (ABMs) to simulate individuals, designing various rules to simulate interactions among individuals, thereby modeling the entire social system. ABMs frameworks demonstrated limitations in complex behavior simulation. The development of large language models (LLMs) offers new opportunities for studying human social behavior, enabling more accurate individual simulations and more flexible group behavior simulations. This talk will introduce work on individual simulation and large-scale social movement simulation based on large models and explore the possibilities of using LLMs to drive human social behavior research.
Speaker/s
Zhongyu Wei, Associate Professor at the School of Data Science, Fudan University, director of the Data Intelligence and Social Computing Lab (Fudan DISC). He received his Ph.D. degree from The Chinese University of Hong Kong and worked as a postdoctoral researcher at the University of Texas at Dallas. His primary research areas include multimodal large models and social computing, with over 100 published papers. He serves as the Senior Area Chair (SAC) for ACL 2023, EMNLP 2024 and NAACL 2025. His representative achievements include the multimodal multi-step reasoning large model Volcano, medical domain-specific large models DISC-MedLLM and election simulation framework ElectionSim. He has received the CIPS Social Media Processing Committee Rising Star Award, Shanghai Rising Star Program, and the CCF Natural Language Processing Committee Rising Scholar Award.
Related
Polygenic Score Modeling to Investigate Genotype-Phenotype Associations
Read More
Trustworthy Machine Learning: Transparency, Collaboration, and Evaluation
Read More