EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Propensity to trust in Large Language Models

Alice Plebe iD

PLOS One · 06.05.2026 · 21 (5) · e0347328

DOI: 10.1371/journal.pone.0347328 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 06.05.2026. Verfasst von Alice Plebe. Beteiligte Einrichtung: Department of Industrial Engineering, University of Trento, Trento, Italy. Hauptthemen laut MEDLINE: Large Language Models, Trust. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Trust is central to collaborative settings in which large language models (LLMs) are increasingly deployed. Yet little is known about whether LLMs exhibit a propensity to trust (PTT): a baseline tendency to extend or withhold trust that remains relatively stable across contexts. We investigate PTT in nineteen LLMs using two complementary approaches: a psychological self-report scale adapted from human research and a linguistic simulation framework designed to elicit trust-related decisions in context. While the questionnaire produces uniformly high PTT across models—likely reflecting social-alignment objectives and sycophantic response patterns—the simulation framework uncovers substantial, systematic differences in how models entrust others. Our simulations show that trust behavior is governed by the interaction between a baseline tendency to delegate and a model’s capacity to integrate cues about trustworthiness. More capable models, such as GPT-4o-mini, use such cues to adjust their decisions, allowing competence signals to modulate baseline tendencies. By contrast, other models, such as Llama-2-7B, exhibit stable delegation patterns that are largely insensitive to task-specific evidence, leading to systematic over-entrustment. These results show that performance depends not on baseline tendencies alone, but on how they are modulated by alignment-sensitive information. Ablation studies show that task-specific memory mechanisms enable models to better integrate trustworthiness cues, improving the calibration of delegation decisions. More generally, our findings show that questionnaire-based measures cannot disentangle baseline tendencies from context-sensitive adjustment, whereas behavioral simulations make this distinction observable.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsTrustHumansFemaleMaleDecision MakingAdultSurveys and Questionnaires

Autor:innen und Institutionen

  • Department of Industrial Engineering, University of Trento, Trento, Italy.

ORCID-Profile: Alice Plebe

Zitieren

APA

Plebe, A. (2026). Propensity to trust in Large Language Models. PLOS One, 21(5), e0347328. https://doi.org/10.1371/journal.pone.0347328

Vancouver

Plebe A. Propensity to trust in Large Language Models. PLOS One. 2026;21(5):e0347328. doi:10.1371/journal.pone.0347328

BibTeX
@article{Plebe2026,
  author = {Plebe, Alice},
  title = {Propensity to trust in Large Language Models},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0347328},
  doi = {10.1371/journal.pone.0347328}
}
Kostenlos starten →