Xiong & Wu (2025)

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

Acta Psychologica, 260, 105518

Find It

DOI

In Summary

The study compares how humans and LLMs acquire morphological patterns in an artificial language, varying blocked versus interleaved sequencing and juxtaposed versus spaced presentation across verb classification and inflection tasks. The three models tested consistently outperformed humans, showing superior few-shot learning, but diverged from human cognition in three ways. Humans benefited more from interleaving under juxtaposition, consistent with the discriminative contrast hypothesis, while model behaviour was architecture-dependent. Humans benefited from spaced exemplars while models performed better with juxtaposed input. Humans showed a metacognitive illusion, preferring blocked study despite performing better under interleaving, whereas two models consistently returned the interleaving option and one reproduced a human-like misjudgement. The authors conclude that human learning mechanisms such as interleaving and spacing do not transfer straightforwardly to LLMs.

Reference

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

What Rests on This

1 mechanism cites this source. Each finding below is quoted as it appears on that mechanism's own page.

Forgetting Memory Processes

Measured in AI

In an artificial-language study of spacing, three LLMs (including DeepSeek-V3 and Llama 3.1) outperformed people but, unlike people, did better with examples placed side by side than spaced apart, and effects varied by model; because the examples stayed in the prompt, the models' higher scores and missing spacing benefit reflect a test with nothing to forget, not a comparison of forgetting