Can Language Models Learn Typologically Implausible Languages?
Transactions of the Association for Computational Linguistics · 15.04.2026 · 14 · 588-611
DOI: 10.1162/tacl.a.640 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 15.04.2026. Verfasst von Tianyang Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 102 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Grammatical features across human languages exhibit intriguing correlations, often attributed to learning biases in humans. Language models (LMs) provide a scalable and naturalistic framework for studying artificial language learning—one not available in human research. We investigate how learnability varies across typologically plausible and implausible languages that closely follow the word order universals identified by linguistic typologists. Our study trains LMs on highly naturalistic counterfactual versions of English (head-initial) and Japanese (head-final). Compared to prior work, our datasets more precisely target the boundary between typological plausibility and implausibility. Our experiments show that LMs learn subtly implausible languages more slowly, though they eventually reach similar performance on some metrics regardless of typological plausibility. These findings suggest that LMs exhibit typologically aligned learning preferences and that certain typological patterns may emerge from general learning biases. https://github.com/sally-xu-42/Typological_Universals.
Zitieren
APA
Xu, T., Kuribayashi, T., Oseki, Y., Cotterell, R., & Warstadt, A. (2026). Can Language Models Learn Typologically Implausible Languages?. Transactions of the Association for Computational Linguistics, 14, 588-611. https://doi.org/10.1162/tacl.a.640
Vancouver
Xu T, Kuribayashi T, Oseki Y, Cotterell R, Warstadt A. Can Language Models Learn Typologically Implausible Languages?. Transactions of the Association for Computational Linguistics. 2026;14:588-611. doi:10.1162/tacl.a.640
BibTeX
@article{Xu2026,
author = {Xu, Tianyang and Kuribayashi, Tatsuki and Oseki, Yohei and Cotterell, Ryan and Warstadt, Alex},
title = {Can Language Models Learn Typologically Implausible Languages?},
journal = {Transactions of the Association for Computational Linguistics},
year = {2026},
volume = {14},
pages = {588--611},
doi = {10.1162/tacl.a.640}
}
EUVIMED