CoChat

Should large language models replace human participants?

Open access
Crockett, Molly, Messeri, Lisa · 2023
PreprintCited by 40

The DOI matches its Crossref record.

Abstract

Recent advances in large language models (LLMs) like OpenAI’s GPT-4 and Alphabet’s Bard have captivated people around the world, including cognitive scientists. Recently, Dillion et al. [1] asked whether LLMs can replace human participants in cognitive science research, noting some of the limitations of these models and offering a framework for integrating them into a cognitive science research pipeline. Here, we suggest that alongside asking whether LLMs can replace human participants, we ought to critically consider whether they should. What are we assuming when we explore the possibility of treating LLMs as proxies for human participants? And what are the costs of those assumptions? Examining these questions offers opportunities for us to reflect on our values as a field.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.31234/osf.io/4zdx9

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cited by

See all 40

Metadata

Authors
Crockett, M., & Messeri, L.
Published
2023-06-19
OpenAlex
W4381163899
Cited by
40
References
0
Type
posted content
Language
en
Open access
gold

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Should large language models replace human participants? https://app.cochat.ai/papers/10.31234/osf.io/4zdx9
The paper
Crockett, M., & Messeri, L. (2023). Should large language models replace human participants? https://doi.org/10.31234/osf.io/4zdx9

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.