arXiv 2405.197442024-05-30cs.CLcs.AI

X-Instruction：利用自整理的跨语言指令对齐低资源语言的语言模型

X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions

State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Institute of Automation, CAS（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

Chong Li, Wen Yang, Jiajun Zhang, Jinliang Lu, Shaonan Wang, Chengqing Zong

备注：: ACL 2024. Our codes, data and model weights are available at https://github.com/ZNLP/X-Instruction

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出X-Instruction方法，通过自整理跨语言指令（英语指令+低资源语言响应）构建大规模数据集，显著提升低资源语言模型响应质量，达到或超越ChatGPT水平。

摘要：

大型语言模型在高资源语言（如英语）中响应良好，但在低资源语言中表现不佳。这可能是由于这些语言缺乏高质量的指令遵循数据。直接将英语样本翻译成这些语言可能是一种解决方案，但不可靠，会导致响应出现翻译错误，且缺乏特定语言或文化知识。为了解决这个问题，我们提出了一种新方法，用于构建跨语言指令遵循样本，其中指令为英语，响应为低资源语言。具体来说，语言模型首先学习根据其他语言的自然网络文本作为响应来生成合适的英语指令。候选的跨语言指令微调样本被进一步优化和多样化。我们已使用该方法在10种语言上构建了一个大规模跨语言指令微调数据集，即X-Instruction。与简单的翻译方法相比，使用我们方法构建的指令数据融入了更多特定语言的知识。实验结果表明，在X-Instruction上微调的模型的响应质量大大超过了从强大教师模型蒸馏的模型，达到甚至超过了ChatGPT的水平。此外，我们发现，在跨语言指令遵循样本上微调的模型能够遵循输出语言中的指令，而无需进一步微调。

英文摘要：

Large language models respond well in high-resource languages like English but struggle in low-resource languages. It may arise from the lack of high-quality instruction following data in these languages. Directly translating English samples into these languages can be a solution but unreliable, leading to responses with translation errors and lacking language-specific or cultural knowledge. To address this issue, we propose a novel method to construct cross-lingual instruction following samples with instruction in English and response in low-resource languages. Specifically, the language model first learns to generate appropriate English instructions according to the natural web texts in other languages as responses. The candidate cross-lingual instruction tuning samples are further refined and diversified. We have employed this method to build a large-scale cross-lingual instruction tuning dataset on 10 languages, namely X-Instruction. The instruction data built using our method incorporate more language-specific knowledge compared with the naive translation method. Experimental results have shown that the response quality of the model tuned on X-Instruction greatly exceeds the model distilled from a powerful teacher model, reaching or even surpassing the ones of ChatGPT. In addition, we find that models tuned on cross-lingual instruction following samples can follow the instruction in the output language without further tuning.

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。