EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Can large language models be viewed as a cognitive model of human language? Not yet, regardless of reasoning capability and size

Haerim Hwang

Acta Psychologica · 2026-07 · 267 · 107025

DOI: 10.1016/j.actpsy.2026.107025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Psychologica, 2026-07. Verfasst von Haerim Hwang. Beteiligte Einrichtung: Department of English, The Chinese University of Hong Kong, Hong Kong. Electronic address: haerimhwang@cuhk.edu.hk. Hauptthemen laut MEDLINE: Large Language Models, Cognition, Language, Psycholinguistics. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Chinese University of Hong Kong.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Can large language models (LLMs) be viewed as a cognitive model of human language? Do they possess human-like language competence? To address these questions, this study takes a multifaceted approach, comparing the performance of 10 recent LLMs (n = 4000 responses) and 94 humans (n = 3760 responses) on grammaticality judgments and sentence interpretations, focusing on five linguistic phenomena that involve missing material. The analyses show that while the LLMs appeared to differentiate between grammatical/possible and ungrammatical/impossible sentences/interpretations overall, they struggled with infrequent phenomena (e.g., Gapping, Sluicing), often rejecting grammatical sentences and accepting impossible interpretations. Notably, increased size seemed to improve their performance on grammaticality judgments, but neither size nor reasoning capability improved their performance on interpretation. In contrast, humans demonstrated a clear sensitivity to these distinctions. The findings seem to align with the view that LLMs, in their current form, lack language competence and do not provide a convincing explanation of human language.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsCognitionLanguagePsycholinguisticsHumansFemaleAdultMaleJudgmentYoung Adult

Stichwörter der Autor:innen

Grammaticality judgmentInterpretationLarge language modelModel sizeReasoning capabilitySilent structure

Autor:innen und Institutionen

  • Department of English, The Chinese University of Hong Kong, Hong Kong. Electronic address: haerimhwang@cuhk.edu.hk.

Förderung

  • Chinese University of Hong Kong

Zitieren

APA

Hwang, H. (2026). Can large language models be viewed as a cognitive model of human language? Not yet, regardless of reasoning capability and size. Acta Psychologica. https://doi.org/10.1016/j.actpsy.2026.107025

Vancouver

Hwang H. Can large language models be viewed as a cognitive model of human language? Not yet, regardless of reasoning capability and size. Acta Psychologica. 2026. doi:10.1016/j.actpsy.2026.107025

BibTeX
@article{Hwang2026,
  author = {Hwang, Haerim},
  title = {Can large language models be viewed as a cognitive model of human language? Not yet, regardless of reasoning capability and size},
  journal = {Acta Psychologica},
  year = {2026},
  doi = {10.1016/j.actpsy.2026.107025}
}
Kostenlos starten →