Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulation
Evaluating six matched base and post-trained models on the Pew American Trends Panel, it is found that base models are the stronger emulators: they produce response distributions closer to human ground truth and better preserve demographic structure.
Seth Grief-Albert, Jessica Y. Bo, Di-Fan Jiao et al.
· 0 citations