Do Large Language Models Know What Humans Know?
Cognitive Science · 2023-07 · 47 (7)
DOI: 10.1111/cogs.13309 ↗At a glance
Journal article in Cognitive Science, published online on 2023-07-04. Written by Sean Trott and 4 co-authors. Institution: Department of Cognitive Science, University of California San Diego. Major MEDLINE topics: Communication, Theory of Mind. Cited 91 times so far (Crossref); 77 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Humans can attribute beliefs to others. However, it is unknown to what extent this ability results from an innate biological endowment or from experience accrued through child development, particularly exposure to language describing others' mental states. We test the viability of the language exposure hypothesis by assessing whether models exposed to large quantities of human language display sensitivity to the implied knowledge states of characters in written passages. In pre‐registered analyses, we present a linguistic version of the False Belief Task to both human participants and a large language model, GPT‐3. Both are sensitive to others' beliefs, but while the language model significantly exceeds chance behavior, it does not perform as well as the humans nor does it explain the full extent of their behavior—despite being exposed to more language than a human would in a lifetime. This suggests that while statistical learning from language exposure may in part explain how humans develop the ability to reason about the mental states of others, other mechanisms are also responsible.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Cognitive Science, University of California San Diego.
Cite
APA
Trott, S., Jones, C., Chang, T., Michaelov, J., & Bergen, B. (2023). Do Large Language Models Know What Humans Know?. Cognitive Science, 47(7). https://doi.org/10.1111/cogs.13309
Vancouver
Trott S, Jones C, Chang T, Michaelov J, Bergen B. Do Large Language Models Know What Humans Know?. Cognitive Science. 2023;47(7). doi:10.1111/cogs.13309
BibTeX
@article{Trott2023,
author = {Trott, Sean and Jones, Cameron and Chang, Tyler and Michaelov, James and Bergen, Benjamin},
title = {Do Large Language Models Know What Humans Know?},
journal = {Cognitive Science},
year = {2023},
volume = {47},
number = {7},
doi = {10.1111/cogs.13309}
}
EUVIMED