# Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas

**Published:** October 6, 2026
**Author:** Khashayar Pourtaheri, Ahmad Zareei
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/behavioral-history-outperforms-descriptions-of-the-person-for-llm-synthe

Large language models (LLMs) are increasingly used as synthetic personas representing survey respondents. Their validity as substitutes for particular respondents depends on whether they reproduce individuals' decisions. We examine what information helps synthetic respondents…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.03998)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*