Cookies?
Library Header Image
LSE Research Online LSE Library Services

Diminished diversity-of-thought in a standard large language model

Park, Peter S., Schoenegger, Philipp ORCID: 0000-0001-9930-487X and Zhu, Chongyang (2024) Diminished diversity-of-thought in a standard large language model. Behavior Research Methods, 56 (6). 5754 - 5770. ISSN 1554-351X

[img] Text (Schoenegger_diminished-diversity-of-thought--published) - Published Version
Available under License Creative Commons Attribution.

Download (1MB)

Identification Number: 10.3758/s13428-023-02307-x

Abstract

We test whether large language models (LLMs) can be used to simulate human participants in social-science studies. To do this, we ran replications of 14 studies from the Many Labs 2 replication project with OpenAI’s text-davinci-003 model, colloquially known as GPT-3.5. Based on our pre-registered analyses, we find that among the eight studies we could analyse, our GPT sample replicated 37.5% of the original results and 37.5% of the Many Labs 2 results. However, we were unable to analyse the remaining six studies due to an unexpected phenomenon we call the “correct answer” effect. Different runs of GPT-3.5 answered nuanced questions probing political orientation, economic preference, judgement, and moral philosophy with zero or near-zero variation in responses: with the supposedly “correct answer.” In one exploratory follow-up study, we found that a “correct answer” was robust to changing the demographic details that precede the prompt. In another, we found that most but not all “correct answers” were robust to changing the order of answer choices. One of our most striking findings occurred in our replication of the Moral Foundations Theory survey results, where we found GPT-3.5 identifying as a political conservative in 99.6% of the cases, and as a liberal in 99.3% of the cases in the reverse-order condition. However, both self-reported ‘GPT conservatives’ and ‘GPT liberals’ showed right-leaning moral foundations. Our results cast doubts on the validity of using LLMs as a general replacement for human participants in the social sciences. Our results also raise concerns that a hypothetical AI-led future may be subject to a diminished diversity of thought.

Item Type: Article
Official URL: https://link.springer.com/journal/13428
Additional Information: © 2024 The Author(s)
Divisions: Management
Subjects: B Philosophy. Psychology. Religion > BF Psychology
T Technology > T Technology (General)
Date Deposited: 18 Jan 2024 10:33
Last Modified: 10 Oct 2024 22:45
URI: http://eprints.lse.ac.uk/id/eprint/121403

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics