דגמים מוכנים של תערובת דמויות ודגמים זוגיים לחקר אדם

תקציר מקורי באנגליתarXiv:2609.22607v2 Announce Type: replace Abstract: 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) for well-calibrated human models, currently realized as pretrained base models. We show that PMMs produce more accurate predictions than instruction-t