@inproceedings{ahuja-etal-2025-sphinx,
    title = "s{P}hin{X}: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting",
    author = "Ahuja, Sanchit  and
      Tanmay, Kumar  and
      Chauhan, Hardik Hansrajbhai  and
      Patra, Barun  and
      Aggarwal, Kriti  and
      Corro, Luciano Del  and
      Mitra, Arindam  and
      Dhamecha, Tejas Indulal  and
      Awadallah, Ahmed Hassan  and
      Choudhury, Monojit  and
      Chaudhary, Vishrav  and
      Sitaram, Sunayana",
    editor = "Dhole, Kaustubh  and
      Clinciu, Miruna",
    booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})",
    month = jul,
    year = "2025",
    address = "Vienna, Austria and virtual meeting",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.gem-1.73/",
    pages = "927--946",
    ISBN = "979-8-89176-261-9",
    abstract = "Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively augmenting English instruction-response pairs with multilingual translations. Additionally, we propose LANGIT, a novel N-shot guided fine-tuning strategy, which further enhances model performance by incorporating contextually relevant examples in each training sample. Our ablation study shows that our approach enhances the multilingual capabilities of Mistral-7B and Phi-3-Small improving performance by an average of 39.8{\%} and 11.2{\%}, respectively, across multilingual benchmarks in reasoning, question answering, reading comprehension, and machine translation. Moreover, sPhinX maintains strong performance on English LLM benchmarks while exhibiting minimal to no catastrophic forgetting, even when trained on 51 languages."
}