Can Large Language Models Generalize Analogy Solving Like Children Can?
Transactions of the Association for Computational Linguistics · 15.04.2026 · 14 · 612-626
DOI: 10.1162/tacl.a.614 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 15.04.2026. Verfasst von Claire E. Stevenson und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Kinderkrankenpflege
Abstract (Originalsprache)
In people, the ability to solve analogies such as “body: feet:: table: ?” emerges in childhood, and appears to transfer easily to other domains, such as the visual domain “(: ) :: < : ?”. Recent research shows that large language models (LLMs) can solve various forms of analogies. However, can LLMs generalize analogy solving to other domains like people can? To investigate this, we had children, adults, and LLMs solve a series of letter-string analogies (e.g., a b : a c :: j k : ?) in the Latin alphabet, in a near transfer domain (Greek alphabet), and a far transfer domain (list of symbols). Children and adults easily generalized their knowledge to unfamiliar domains, whereas LLMs did not. This key difference between human and AI performance is evidence that these LLMs still struggle with robust human-like analogical transfer.
Zitieren
APA
Stevenson, C. E., Pafford, A., Maas, H. L. J. V. D., & Mitchell, M. (2026). Can Large Language Models Generalize Analogy Solving Like Children Can?. Transactions of the Association for Computational Linguistics, 14, 612-626. https://doi.org/10.1162/tacl.a.614
Vancouver
Stevenson CE, Pafford A, Maas HLJVD, Mitchell M. Can Large Language Models Generalize Analogy Solving Like Children Can?. Transactions of the Association for Computational Linguistics. 2026;14:612-626. doi:10.1162/tacl.a.614
BibTeX
@article{Stevenson2026,
author = {Stevenson, Claire E. and Pafford, Alexandra and Maas, Han L. J. van der and Mitchell, Melanie},
title = {Can Large Language Models Generalize Analogy Solving Like Children Can?},
journal = {Transactions of the Association for Computational Linguistics},
year = {2026},
volume = {14},
pages = {612--626},
doi = {10.1162/tacl.a.614}
}
EUVIMED