@inproceedings{shani-basirat-2025-language,
    title = "Language Dominance in Multilingual Large Language Models",
    author = "Shani, Nadav  and
      Basirat, Ali",
    editor = "Belinkov, Yonatan  and
      Mueller, Aaron  and
      Kim, Najoung  and
      Mohebbi, Hosein  and
      Chen, Hanjie  and
      Arad, Dana  and
      Sarti, Gabriele",
    booktitle = "Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.blackboxnlp-1.7/",
    pages = "137--148",
    ISBN = "979-8-89176-346-3",
    abstract = "This paper investigates the language dominance hypothesis in multilingual large language models (LLMs), which posits that cross-lingual understanding is facilitated by an implicit translation into a dominant language seen more frequently during pretraining. We propose a novel approach to quantify how languages influence one another in a language model. By analyzing the hidden states across intermediate layers of language models, we model interactions between language-specific embedding spaces using Gaussian Mixture Models. Our results reveal only weak signs of language dominance in middle layers, affecting only a fraction of tokens. Our findings suggest that multilingual processing in LLMs is better explained by language-specific and shared representational spaces rather than internal translation into a single dominant language."
}