Will Scaling Improve Social Simulation with LLMs?

Caleb Ziems, William Held, Su Doga Karaca, David Grusky, Tatsunori Hashimoto et al.|July 2, 2026arXiv

Key Takeaway

Larger LLMs will simulate most human behaviors and opinions better, but scaling alone won't fix simulations of cognitive biases, rare populations, or tasks requiring specialized human knowledge—these need targeted research beyond just bigger models.

Summary

This paper investigates whether scaling up language models improves their ability to simulate human social behavior and opinions.

evaluation scaling applications

Key Terms

scaling-laws social-simulation model-calibration behavioral-simulation opinion-modeling