# Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies

*Source* · `src-aher-2022-turing-experiments` · status: **n/a**

| field | value |
|---|---|
| kind | Preprint |
| authors | Gati Aher, Rosa I. Arriaga, Adam Tauman Kalai |
| venue | arXiv |
| date | 2022-08-18 |
| url | https://arxiv.org/abs/2208.10264 |
| arxiv | 2208.10264 |
| accessed | 2026-10-24 |

## Notes

Turing Experiments: models replicated Ultimatum Game, garden path sentence, and Milgram shock findings; a wisdom-of-crowds experiment revealed a hyper-accuracy distortion in ChatGPT and GPT-4.

## Backlinks (computed)

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

## Citation

Gati Aher, Rosa I. Arriaga, Adam Tauman Kalai (2022-08-18). *Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies*. arXiv https://arxiv.org/abs/2208.10264

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