LLaMA Beyond English: An Empirical Study on Language Capability Transfer

TL;DR

This paper empirically investigates how to transfer LLaMA's language capabilities to non-English languages, analyzing factors like vocabulary extension and instruction tuning, and demonstrating effective transfer with minimal pretraining data across multiple languages.

Contribution

It provides a comprehensive empirical study on transferring LLaMA's capabilities to non-English languages, highlighting effective methods and minimal data requirements.

Findings

Comparable performance achieved with less than 1% pretraining data

Effective transfer demonstrated across 13 low-resource languages

Evaluation shows maintained response quality and knowledge alignment

Abstract

In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks. However, many mainstream LLMs (e.g. LLaMA) are pretrained on English-dominant corpus, which limits their performance in other non-English languages. In this paper, we focus on how to effectively transfer the capabilities of language generation and following instructions to a non-English language. To answer this question, we conduct an extensive empirical investigation based on LLaMA, accumulating over 1440 GPU hours. We analyze the impact of key factors such as vocabulary extension, further pretraining, and instruction tuning on transfer. To accurately assess the model's level of knowledge, we employ four widely used standardized testing benchmarks: C-Eval, MMLU, AGI-Eval, and GAOKAO-Bench. Furthermore, a comprehensive evaluation of the model's response quality is conducted, considering aspects such as accuracy, fluency, informativeness, logical coherence, and harmlessness, based on LLM-Eval, a benchmarks consisting instruction tasks from 17 diverse categories. Our evaluation results demonstrate that comparable performance to state-of-the-art transfer models can be achieved with less than 1% of the pretraining data, both in terms of knowledge alignment and response quality. Furthermore, the experimental outcomes across the thirteen low-resource languages also exhibit similar trends. We anticipate that the conclusions revealed by the experiments will aid the community in developing non-English LLMs.