为极低资源和濒危语言进行推理迁移：通过高效样本的语言理解连接语言
Reasoning Transfer for an Extremely Low-Resource and Endangered Language: Bridging Languages Through Sample-Efficient Language Understanding
AI总结：
本文提出英语引导的Co T训练方法，通过监督微调提升极低资源语言的推理能力，并发布首个爱尔兰语数学任务基准测试，展示多语言推理的可行路径。
摘要：
最近的进展使大型语言模型（LLMs）能够通过生成思路链（CoT）推理过程来解决推理任务，但这些进展主要应用于高资源语言，使低资源语言处于落后状态。在本工作中，我们首先通过先前的提示、模型编辑和微调方法研究了Co T技术在极低资源场景中的应用。我们引入了英语引导的Co T训练，利用LLMs内部在主导语言方向上对齐的潜在空间的洞察。在输入为低资源语言的情况下，我们通过监督微调生成英文的Co T并输出目标语言的最终响应。在数学推理基准测试中，我们的方法在低资源场景中比其他基线提高了高达28.33%。我们的分析和额外的实验，包括混合语言Co T和两阶段训练，表明显式分离语言理解和推理可以增强跨语言推理能力。为了促进未来的工作，我们还发布了LC2024，这是首个针对爱尔兰语（一种极低资源和濒危语言）数学任务的基准测试。我们的结果和资源展示了在没有对每个极低资源语言进行大量重新训练的情况下，实现多语言推理的可行路径，尽管数据稀缺。
英文摘要：
Recent advances have enabled Large Language Models (LLMs) to tackle reasoning tasks by generating chain-of-thought (CoT) rationales, yet these gains have largely applied to high-resource languages, leaving low-resource languages behind. In this work, we first investigate CoT techniques in extremely low-resource scenarios through previous prompting, model-editing, and fine-tuning approaches. We introduce English-Pivoted CoT Training, leveraging the insight that LLMs internally operate in a latent space aligned toward the dominant language. Given input in a low-resource language, we perform supervised fine-tuning to generate CoT in English and output the final response in the target language. Across mathematical reasoning benchmarks, our approach outperforms other baselines with up to 28.33% improvement in low-resource scenarios. Our analysis and additional experiments, including Mixed-Language CoT and Two-Stage Training, show that explicitly separating language understanding from reasoning enhances cross-lingual reasoning abilities. To facilitate future work, we also release \emph{LC2024}, the first benchmark for mathematical tasks in Irish, an extremely low-resource and endangered language. Our results and resources highlight a practical pathway to multilingual reasoning without extensive retraining in every extremely low-resource language, despite data scarcity.
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。
