@inproceedings{zhou-matusevych-2025-curse,
    title = "Curse of bilinguality: Evaluating monolingual and bilingual language models on {C}hinese linguistic benchmarks",
    author = "Zhou, Yuwen  and
      Matusevych, Yevgen",
    editor = "Dhole, Kaustubh  and
      Clinciu, Miruna",
    booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})",
    month = jul,
    year = "2025",
    address = "Vienna, Austria and virtual meeting",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.gem-1.58/",
    pages = "622--630",
    ISBN = "979-8-89176-261-9",
    abstract = "We investigate cross-lingual transfer effects in large language models (LLMs) trained on two high-resource languages, English and Chinese. Four monolingual Chinese and four bilingual English{--}Chinese models are evaluated on two Chinese linguistic benchmarks. The monolingual models consistently outperform the bilingual ones on 12 out of 55 tasks, while the reverse is true for only 4 tasks, highlighting the prevalence of negative (rather than positive) transfer from English to Chinese. Additionally, we carry out a feature attribution analysis in a monolingual and a bilingual model, showing that the differences in their performance may be explained by more predictable attribution patterns in the monolingual model. Our findings have implications for the ongoing effort of training bilingual LLMs."
}