arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15378cs.CL
收藏

让大语言模型开口说图鲁语:一种结构化提示方法用于极低资源语言

Making Large Language Models Speak Tulu: Structured Prompting for an Extremely Low-Resource Language

Lossfunk

Prathamesh Devadiga, Paras Chopra

AI总结:

本研究通过结构化提示方法,在极低资源语言图鲁语上实现基本对话能力,减少词汇污染并提高语法准确性。

摘要:

大语言模型能否在训练数据中几乎不存在的语言中进行对话?我们通过图鲁语的案例研究来探讨这个问题。图鲁语是一种有超过200万使用者的德拉维达人语言,但数字存在极少。而不是对LLM进行微调,我们检查在受控提示下,仅使用结构化提示是否能引发基本的对话能力。我们通过结合显式的语法规则文档、负约束以抑制相关语言的高概率标记、罗马化标准化以及通过自博弈生成的高质量合成数据,系统地解决图鲁语训练数据缺乏带来的各种挑战。在三个LLM(Gemini 2.0 Flash、GPT-4o、Llama 3.1 70B)上手动整理的验证集上进行评估,并由母语者验证,我们的方法将词汇污染从80%降至5%,同时实现了85%的语法准确性。跨模型分析显示,负约束提供了一致的改进(12-18个百分点),而语法规则文档的效果则因模型架构而异(8-22个百分点)。

英文摘要:

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).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑