仅需少量多语言性的多语言指导调整

摘要

随着调整后的大型语言模型（LLMs）在全球范围内得到广泛应用，其在多种语言中遵循指令的能力变得日益关键。一种有前途的方法是跨语言迁移，即模型通过在另一种语言上微调来获得某种语言上的特定功能。在这项工作中，我们研究了多语言LLM在指令调整过程中如何影响跨语言指令遵循。我们首先展示了许多语言从单语调整中甚至可以将一些指令遵循能力转移到其他语言。此外，我们发现在英语调整集中仅有40个多语言示例就能显著提高跨语言指令遵循，无论是在调整过程中见过的还是未见过的语言中。总的来说，我们观察到在多语言混合调整的模型在多种语言中表现出与单语调整模型相当或更优越的性能，尽管在这些语言中的训练示例要少10倍。最后，我们发现将指令调整集中的语言数量从1增加到2、3或4会增加跨语言泛化能力。我们的结果表明，只需一个非常小的多语言指令-响应集合，就可以构建大规模多语言指令调整模型。

English

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. One promising approach is cross-lingual transfer, where a model acquires specific functionality on some language by finetuning on another language. In this work, we investigate how multilinguality during instruction tuning of a multilingual LLM affects instruction-following across languages. We first show that many languages transfer some instruction-following capabilities to other languages from even monolingual tuning. Furthermore, we find that only 40 multilingual examples in an English tuning set substantially improve multilingual instruction-following, both in seen and unseen languages during tuning. In general, we observe that models tuned on multilingual mixtures exhibit comparable or superior performance in several languages compared to monolingually tuned models, despite training on 10x fewer examples in those languages. Finally, we find that increasing the number of languages in the instruction tuning set from 1 to only 2, 3, or 4 increases cross-lingual generalization. Our results suggest that building massively multilingual instruction-tuned models can be done with only a very small set of multilingual instruction-responses.

仅需少量多语言性的多语言指导调整

Multilingual Instruction Tuning With Just a Pinch of Multilinguality

摘要

Support