@inproceedings{haider-etal-2025-robustness,
    title = "Robustness of {LLM}s to Transliteration Perturbations in {B}angla",
    author = "Haider, Fabiha  and
      Ishmam, Md Farhan  and
      Shifat, Fariha Tanjim  and
      Adib, Md Tasmim Rahman  and
      Fahim, Md  and
      Bhuiyan, Md Farhad Alam",
    editor = "Alam, Firoj  and
      Kar, Sudipta  and
      Chowdhury, Shammur Absar  and
      Hassan, Naeemul  and
      Prince, Enamul Hoque  and
      Tasnim, Mohiuddin  and
      Rony, Md Rashad Al Hasan  and
      Rahman, Md Tahmid Rahman",
    booktitle = "Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.banglalp-1.27/",
    pages = "338--346",
    ISBN = "979-8-89176-314-2",
    abstract = "Bangla text on the internet often appears in mixed scripts that combine native Bangla characters with their Romanized transliterations. To ensure practical usability, language models should be robust to naturally occurring script mixing. Our work investigates the robustness of current LLMs and Bangla language models under various transliteration-based textual perturbations, \textit{i.e.}, we augment portions of existing Bangla datasets using transliteration. Specifically, we replace words and sentences with their transliterated text to emulate realistic script mixing, and similarly, replace the top k salient words to emulate adversarial script mixing. Our experiments reveal interesting behavioral insights and vulnerabilities to robustness in language models for Bangla, which can be crucial for deploying such models in real-world scenarios and enhancing their overall robustness."
}