用结构化提示让大模型说冷门语言，不微调也能懂语法。
Making Large Language Models Speak Tulu: Structured Prompting for an Extremely Low-Resource Language
- 用规则+负约束+自生成数据，让模型避开母语干扰。
- 语法准确率达85%，词汇混淆从80%降到5%。
- 适合想低成本拓展低资源语言的开发者或研究者。
大语言模型能否在训练数据极少的语言中进行对话？我们以拥有200多万使用者但数字资源匮乏的德拉维达语塔鲁语为例展开研究。不通过微调，仅依靠结构化提示能否激发其基本对话能力？我们系统应对塔鲁语缺乏训练数据带来的挑战，结合显式语法文档、抑制相关语言高概率词项的负约束、罗马化标准化以及通过自对弈生成的质量可控合成数据。在三个大模型（Gemini 2.0 Flash、GPT-4o、Llama 3.1 70B）上评估，并经母语者验证，该方法使词汇污染率从80%降至5%，语法准确率达到85%。跨模型分析显示，负约束带来12–18个百分点的一致提升，而语法文档的效果因模型架构不同而异（8–22个百分点）。
原文摘要 · Abstract (English)
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 2 million speakers but minimal digital presence. Rather than fine-tuning an LLM, we examine whether structured prompts alone can elicit basic conversational ability under controlled prompting. We systematically tackle various challenges posed by absence of training data for Tulu by combining 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, 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 reveals that negative constraints provide consistent improvements (12--18 percentage points), while grammar documentation effects vary by model architecture (8--22 points).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。