Authors: Gati Aher, Rosa I. Arriaga, Adam Tauman Kalai
@inproceedings{turingExp22,
title={Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies},
author={Aher, Gati V and Arriaga, Rosa I and Kalai, Adam Tauman},
booktitle={Proceedings of the 40th International Conference on Machine Learning (ICML)},
year={2023},
url={https://arxiv.org/abs/2208.10264},
organization={PMLR}
}
Submitted to arXiv on August 18, 2022.
Abstract: We introduce a new type of test, called a Turing Experiment (TE), for evaluating to what extent a given language model, such as GPT models, can simulate different aspects of human behavior. A TE can also reveal consistent distortions in a language model's simulation of a specific human behavior. Unlike the Turing Test, which involves simulating a single arbitrary individual, a TE requires simulating a representative sample of participants in human subject research. We carry out TEs that attempt to replicate well-established findings from prior studies. We design a methodology for simulating TEs and illustrate its use to compare how well different language models are able to reproduce classic economic, psycholinguistic, and social psychology experiments: Ultimatum Game, Garden Path Sentences, Milgram Shock Experiment, and Wisdom of Crowds. In the first three TEs, the existing findings were replicated using recent models, while the last TE reveals a "hyper-accuracy distortion" present in some language models (including ChatGPT and GPT-4), which could affect downstream applications in education and the arts.
Keywords: Turing Test, Large Language Models, Evaluation Metrics
Code: https://github.com/microsoft/turing-experiments/tree/main