@inproceedings{nguyen-etal-2025-prompting,
    title = "Prompting with Phonemes: Enhancing {LLM}s' Multilinguality for Non-{L}atin Script Languages",
    author = "Nguyen, Hoang H  and
      Mahajan, Khyati  and
      Yadav, Vikas  and
      Salazar, Julian  and
      Yu, Philip S.  and
      Hashemi, Masoud  and
      Maheshwary, Rishabh",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.599/",
    pages = "11975--11994",
    ISBN = "979-8-89176-189-6",
    abstract = "Multilingual LLMs have achieved remarkable benchmark performance, but we find they continue to underperform on non-Latin script languages across contemporary LLM families. This discrepancy arises from the fact that LLMs are pretrained with orthographic scripts, which are dominated by Latin characters that obscure their shared phonology with non-Latin scripts. We propose leveraging phonemic transcriptions as complementary signals to induce script-invariant representations. Our study demonstrates that integrating phonemic signals improves performance across both non-Latin and Latin languages, with a particularly significant impact on closing the performance gap between the two. Through detailed experiments, we show that phonemic and orthographic scripts retrieve distinct examples for in-context learning (ICL). This motivates our proposed Mixed-ICL retrieval strategy, where further aggregation leads to our significant performance improvements for both Latin script languages (up to 12.6{\%}) and non-Latin script languages (up to 15.1{\%}) compared to randomized ICL retrieval."
}