Morphology Matters: Probing the Cross-linguistic Morphological Generalization Abilities of Large Language Models through a Wug Test

Dang Anh, Limor Raviv, Lukas Galke


Abstract
We develop a multilingual version of the Wug Test, an artificial word completion experiment that is typically used to test the morphological knowledge of children, and apply it to the GPT family of large language models (LLMs). LLMs’ performance on this test was evaluated by native speakers of six different languages, who judged whether the inflected and derived forms generated by the models conform to the morphological rules of their language. Our results show that LLMs can generalize their morphological knowledge to new, unfamiliar words, but that their success in generating the “correct” generalization (as judged by native human speakers) is predicted by a language’s morphological complexity (specifically, integrative complexity). We further find that the amount of training data has surprisingly little on LLMs’ morphological generalization abilities within the scope of the analyzed languages. These findings highlight that “morphology matters”, and have important implications for improving low-resource language modeling.
Anthology ID:
2024.cmcl-1.15
Volume:
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Tatsuki Kuribayashi, Giulia Rambelli, Ece Takmaz, Philipp Wicke, Yohei Oseki
Venues:
CMCL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
177–188
Language:
URL:
https://aclanthology.org/2024.cmcl-1.15
DOI:
10.18653/v1/2024.cmcl-1.15
Bibkey:
Cite (ACL):
Dang Anh, Limor Raviv, and Lukas Galke. 2024. Morphology Matters: Probing the Cross-linguistic Morphological Generalization Abilities of Large Language Models through a Wug Test. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 177–188, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Morphology Matters: Probing the Cross-linguistic Morphological Generalization Abilities of Large Language Models through a Wug Test (Anh et al., CMCL-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.cmcl-1.15.pdf