@inproceedings{devadiga-chopra-2026-making,
    title = "Making Large Language Models Speak {T}ulu: Structured Prompting for an Extremely Low-Resource Language",
    author = "Devadiga, Prathamesh  and
      Chopra, Paras",
    editor = "Hettiarachchi, Hansi  and
      Ranasinghe, Tharindu  and
      Plum, Alistair  and
      Rayson, Paul  and
      Mitkov, Ruslan  and
      Gaber, Mohamed  and
      Premasiri, Damith  and
      Tan, Fiona Anting  and
      Uyangodage, Lasitha",
    booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.loreslm-1.5/",
    pages = "50--61",
    ISBN = "979-8-89176-377-7",
    abstract = "Can large language models converse in languages virtually absent from their training data? We investigate this question through a case study on Tulu, a Dravidian language with over two million speakers but minimal digital presence. Rather than fine-tuning, we examine whether structured prompt engineering alone can elicit basic conversational ability under extreme data scarcity. Our framework combines explicit grammar documentation, negative constraints to suppress high-probability tokens from related languages, romanization standardization, and quality-controlled synthetic data generation via self-play. Evaluated on a manually curated held-out set across three LLMs (Gemini 2.0 Flash, GPT-4o, and Llama 3.1 70B) and validated by native speakers, our approach reduces vocabulary contamination from 80{\%} to 5{\%} while achieving 85{\%} grammatical accuracy. Cross-model analysis shows that negative constraints provide consistent improvements (12{--}18 percentage points), while the effectiveness of grammar documentation varies by model architecture (8{--}22 points). These results demonstrate that structured in-context learning can meaningfully extend LLM capabilities to extremely low-resource languages without parameter updates."
}