CoChat

Overlap in meaning is a stronger predictor of semantic activation in GPT-3 than in humans

Open access
Digutsch, Jan, Kosinski, Michal · 2023 · Scientific Reports

Published version of a preprint

The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.

Abstract

Modern large language models generate texts that are virtually indistinguishable from those written by humans and achieve near-human performance in comprehension and reasoning tests. Yet, their complexity makes it difficult to explain and predict their functioning. We examined a state-of-the-art language model (GPT-3) using lexical decision tasks widely used to study the structure of semantic memory in humans. The results of four analyses showed that GPT-3’s patterns of semantic activation are broadly similar to those observed in humans, showing significantly higher semantic activation in related (e.g., “lime–lemon”) word pairs than in other-related (e.g., “sour–lemon”) or unrelated (e.g., “tourist–lemon”) word pairs. However, there are also significant differences between GPT-3 and humans. GPT-3’s semantic activation is better predicted by similarity in words’ meaning (i.e., semantic similarity) rather than their co-occurrence in the language (i.e., associative similarity). This suggests that GPT-3’s semantic network is organized around word meaning rather than their co-occurrence in text.

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 · 10.1038/s41598-023-32248-6

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Semantic activation across priming conditions.
Figure 1 Semantic activation across priming conditions.CC BY · PubMed Central
Figure 2 Semantic activation and prime-target association type. Word pairs in brackets are examples. Error bars represent 95% confidence intervals.
Figure 2 Semantic activation and prime-target association type. Word pairs in brackets are examples. Error bars represent 95% confidence intervals.CC BY · PubMed Central
Figure 3 Semantic activation for associatively (red) and semantically (blue) related words. Dotted lines represent semantic activation for the associatively (red) and semantically (blue) related words in humans.
Figure 3 Semantic activation for associatively (red) and semantically (blue) related words. Dotted lines represent semantic activation for the associatively (red) and semantically (blue) related words in humans.CC BY · PubMed Central

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

Cites

Show all 34 references

Research works printed but not linked: 1

  1. McNamara, T. P. Semantic memory and priming. In Experimental Psychology. Vol. 4 in I. B. Weiner (Editor-in-chief), Handbook of psychology 2nd edn (eds Healy, A. F. & Proctor, R. W.) 449–471 (Wiley, 2013).

Cited by

See all 49

Metadata

Authors
Digutsch, J., & Kosinski, M.
Affiliations
TU Dortmund University (DE)
Corresponding author
Digutsch, Jan
Venue
Scientific Reports
Published
2023-03-28
Volume
13
Issue
1
Pages
5035-5035
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4361204756
Cited by
49
References
31
Citations by year
2026: 7 · 2025: 9 · 2024: 20 · 2023: 12
FWCI
4.52
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Alexandria (UniSG) (University of St.Gallen) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Informationszentrum Lebenswissenschaften (ZB MED) (submittedVersion, cc-by)
  • PsyArXiv (OSF Preprints) (submittedVersion, cc-by)
  • PsyArXiv (OSF Preprints) (submittedVersion)
  • OSF Preprints (OSF Preprints) (submittedVersion)
  • OSF Preprints (OSF Preprints) (submittedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Neurobiology of Language and Bilingualism
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
GPT-3, semantic activation, semantic similarity, lexical decision, semantic memory, large language models, word meaning, word co-occurrence, semantic networks, human-computer comparison
MeSH terms
Humans, Natural Language Processing, Semantics, Word Association Tests, Comprehension

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: Overlap in meaning is a stronger predictor of semantic activation in GPT-3 than in humans. https://app.cochat.ai/papers/10.1038/s41598-023-32248-6
The paper
Digutsch, J., & Kosinski, M. (2023). Overlap in meaning is a stronger predictor of semantic activation in GPT-3 than in humans. Scientific Reports. https://doi.org/10.1038/s41598-023-32248-6

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.