← Search

Sijia Yang

2 accepted papers

2024

Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks

EMNLP 2024finding

Creating human-like large language model (LLM) agents is crucial for faithful social simulation. Having LLMs role-play based on demographic information sometimes improves human likeness but often does not. This study assessed whether LLM alignment with human behavior can be improved by integrating i…

Cited by 11SourcePDFScholar
2024

Simulating Opinion Dynamics with Networks of LLM-based Agents

NAACL 2024findings

Accurately simulating human opinion dynamics is crucial for understanding a variety of societal phenomena, including polarization and the spread of misinformation. However, the agent-based models (ABMs) commonly used for such simulations often over-simplify human behavior. We propose a new approach…