Accentedness ratings of Brazilian speakers’ L2 English by LLMs
Journal of Second Language Pronunciation · 13.11.2026
DOI: 10.1075/jslp.26063.kup ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Second Language Pronunciation, online erschienen am 13.11.2026. Verfasst von Felipe Flores Kupske und 1 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben.
Abstract (Originalsprache)
This study examines whether audio-capable large language models (LLMs) align with human patterns of L2 English accentedness judgment. Google Gemini Flash and Gemini Pro rated the L2 English speech of Brazilian Portuguese speakers from the CSLU Foreign Accented English Corpus ( Lander, 2007 ) and were compared against native American English listeners. Both models assigned systematically more severe ratings, using the highest category of the rating scale at frequencies not observed in the human data. The shift was most pronounced in Gemini Pro ( OR = 8.25), suggesting that greater model capacity does not yield closer alignment with human judgment. The two models also failed to agree with each other. These divergences raise concerns about the validity of LLM accentedness ratings as proxies for human judgment.
Zitieren
APA
Kupske, F. F., & Zorzi, L. (2026). Accentedness ratings of Brazilian speakers’ L2 English by LLMs. Journal of Second Language Pronunciation. https://doi.org/10.1075/jslp.26063.kup
Vancouver
Kupske FF, Zorzi L. Accentedness ratings of Brazilian speakers’ L2 English by LLMs. Journal of Second Language Pronunciation. 2026. doi:10.1075/jslp.26063.kup
BibTeX
@article{Kupske2026,
author = {Kupske, Felipe Flores and Zorzi, Laura},
title = {Accentedness ratings of Brazilian speakers’ L2 English by LLMs},
journal = {Journal of Second Language Pronunciation},
year = {2026},
doi = {10.1075/jslp.26063.kup}
}
EUVIMED