@inproceedings{wang-etal-2025-linguistic,
    title = "The Linguistic Connectivities Within Large Language Models",
    author = "Wang, Dan  and
      Cao, Boxi  and
      Bian, Ning  and
      Chen, Xuanang  and
      Lu, Yaojie  and
      Lin, Hongyu  and
      Zheng, Jia  and
      Sun, Le  and
      Jiang, Shanshan  and
      Dong, Bin  and
      Han, Xianpei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.456/",
    pages = "8700--8714",
    ISBN = "979-8-89176-256-5",
    abstract = "Large language models (LLMs) have demonstrated remarkable multilingual abilities in various applications. Unfortunately, recent studies have discovered that there exist notable disparities in their performance across different languages. Understanding the underlying mechanisms behind such disparities is crucial ensuring equitable access to LLMs for a global user base. Therefore, this paper conducts a systematic investigation into the behaviors of LLMs across 27 different languages on 3 different scenarios, and reveals a Linguistic Map correlates with the richness of available resources and linguistic family relations. Specifically, high-resource languages within specific language family exhibit greater knowledge consistency and mutual information dissemination, while isolated or low-resource languages tend to remain marginalized. Our research sheds light on a deep understanding of LLM{'}s cross-language behavior, highlights the inherent biases in LLMs within multilingual environments and underscores the need to address these inequities."
}