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

Do large language models learn like humans: Interleaved and spaced practice in morphological learning

Ying Xiong, Shiyu Wu

Acta Psychologica · 2025-10 · 260 · 105518

DOI: 10.1016/j.actpsy.2025.105518 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Psychologica, 2025-10. Verfasst von Ying Xiong und 1 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Jiao Tong University, China. Electronic address: xiongying22@sjtu.edu.cn. Hauptthemen laut MEDLINE: Language, Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Shanghai Jiao Tong University, National Social Science Fund of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates fundamental differences in the acquisition of morphological patterns by humans and large language models (LLMs) within an artificial language learning paradigm. Specifically, it compares how each system responds to variations in input structure-blocked versus interleaved sequences and juxtaposed versus spaced presentation-across verb classification and inflection tasks. While LLMs (GPT4mini, DeepSeek_V3, Llama3.1) consistently outperformed humans-demonstrating superior few-shot learning ability-their learning mechanisms diverged sharply from human cognition in three key aspects. First, humans benefited more from interleaved compared to blocked sequences under the juxtaposition condition, consistent with the discriminative contrast hypothesis, whereas LLMs showed model-dependent performance (interleaving effect independent of juxtaposition in GPT4mini / Llama3.1 vs. less sensitivity to input sequencing in DeepSeek_V3). Second, spacing effects revealed a divergence: while human learners benefited from spaced exemplars, LLMs performed better with juxtaposed input. Third, humans exhibited metacognitive illusions-preferring blocked study despite superior interleaved performance-whereas LLMs returned either consistent interleaving option (Llama3.1/DeepSeek_V3) or statistical tendency resembling human misjudgments (GPT4mini). These findings reveal that human learning mechanisms such as interleaving and spacing do not straightforwardly apply to LLMs, and different model architectures mediate input-structure sensitivity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LanguageLearningHumansAdultMaleYoung AdultFemaleLarge Language Models

Stichwörter der Autor:innen

Interleaving effectLarge language models (LLMs)MetacognitionMorphological learningSpacing effect

Autor:innen und Institutionen

  • Shanghai Jiao Tong University, China. Electronic address: xiongying22@sjtu.edu.cn.
  • Shanghai Jiao Tong University, China. Electronic address: shiyuw@sjtu.edu.cn.

Förderung

  • Shanghai Jiao Tong University
  • National Social Science Fund of China

Zitieren

APA

Xiong, Y., & Wu, S. (2025). Do large language models learn like humans: Interleaved and spaced practice in morphological learning. Acta Psychologica, 260, 105518. https://doi.org/10.1016/j.actpsy.2025.105518

Vancouver

Xiong Y, Wu S. Do large language models learn like humans: Interleaved and spaced practice in morphological learning. Acta Psychologica. 2025;260:105518. doi:10.1016/j.actpsy.2025.105518

BibTeX
@article{Xiong2025,
  author = {Xiong, Ying and Wu, Shiyu},
  title = {Do large language models learn like humans: Interleaved and spaced practice in morphological learning},
  journal = {Acta Psychologica},
  year = {2025},
  volume = {260},
  pages = {105518},
  doi = {10.1016/j.actpsy.2025.105518}
}
Kostenlos starten →