SOURCE-LINKED INTELLIGENCE

Pretrained Persona Mixture Models and Tandem Models for Human Simulation

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas, is inaccurate and produces stereotyped predictions (lacking natural diversity). It has previously been shown that LLMs can be bound to personas using naturalistic, freetext dialog avoiding stereotyping. Here we show that binding can also be achieved using short, individual samples of dialog from specific people. Demographics can be added later without negative effects by simply querying the model. We use the term Persona Mixture Models (PMMs) fo

Read original source ↗ Open in workspace

recordType

paper

region

Global