@inproceedings{samantaray-jyothi-2025-cross,
    title = "Cross-lingual Transfer Dynamics in {BLOOMZ}: Insights into Multilingual Generalization",
    author = "Samantaray, Sabyasachi  and
      Jyothi, Preethi",
    editor = "Adelani, David Ifeoluwa  and
      Arnett, Catherine  and
      Ataman, Duygu  and
      Chang, Tyler A.  and
      Gonen, Hila  and
      Raja, Rahul  and
      Schmidt, Fabian  and
      Stap, David  and
      Wang, Jiayi",
    booktitle = "Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)",
    month = nov,
    year = "2025",
    address = "Suzhuo, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/lei-li-partial-disambiguation/2025.mrl-main.4/",
    pages = "47--61",
    ISBN = "979-8-89176-345-6",
    abstract = "Multilingual large language models have emerged as a promising solution for resource-constrained settings, with significant efforts aimed towards improving multilingual capabilities of English-centric pretrained models. However, the broader cross-lingual implications of fine-tuning interventions remain understudied. This work examines instruction tuning (IT) over the BLOOMZ model for Question Answering (QA) in low-resource settings, with special emphasis on transfer dynamics across several languages. Our findings reveal two critical insights: first, IT on the target language can negatively impact its own performance in constrained short-span generation tasks due to overgeneration tendencies; second, in QA tasks, IT appears to suppress performance in some interfering languages, thereby enhancing capabilities in some target Indic languages by $extbf{more than doubling}$ QA performance. These results highlight important trade-offs in multilingual LLM adaptation and enhance our understanding of cross-lingual transfer mechanisms."
}