# Out of One, Many: Using Language Models to Simulate Human Samples

*Source* · `src-argyle-2023-out-of-one-many` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Lisa P. Argyle, Ethan C. Busby, Nancy Fulda, Joshua Gubler, Christopher Rytting, David Wingate |
| venue | Political Analysis |
| date | 2023 |
| url | https://arxiv.org/abs/2209.06899 |
| doi | 10.1017/pan.2023.2 |
| arxiv | 2209.06899 |
| accessed | 2026-10-24 |

## Notes

Silicon samples: GPT-3 conditioned on thousands of sociodemographic backstories from U.S. survey participants reproduces subgroup response distributions; the property is named algorithmic fidelity.

## Backlinks (computed)

**cited by:** [LLM models of individual human choice](../technique/human-behavior-simulation-models.md)

## Citation

Lisa P. Argyle, Ethan C. Busby, Nancy Fulda, Joshua Gubler, Christopher Rytting, David Wingate (2023). *Out of One, Many: Using Language Models to Simulate Human Samples*. Political Analysis https://arxiv.org/abs/2209.06899

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.