Methodology of Adapting Large English Language Models for Specific Cultural Contexts

TL;DR

This paper presents a rapid adaptation method for large language models to better handle specific cultural contexts, demonstrated through Chinese cultural adaptation of LLaMA3-8B, improving domain knowledge and safety value alignment.

Contribution

It introduces a novel instruction-tuning approach leveraging cultural knowledge data to adapt large models for specific cultural contexts efficiently.

Findings

Enhanced domain-specific knowledge in the adapted model

Improved alignment with safety values

Maintained original model capabilities

Abstract

The rapid growth of large language models(LLMs) has emerged as a prominent trend in the field of artificial intelligence. However, current state-of-the-art LLMs are predominantly based on English. They encounter limitations when directly applied to tasks in specific cultural domains, due to deficiencies in domain-specific knowledge and misunderstandings caused by differences in cultural values. To address this challenge, our paper proposes a rapid adaptation method for large models in specific cultural contexts, which leverages instruction-tuning based on specific cultural knowledge and safety values data. Taking Chinese as the specific cultural context and utilizing the LLaMA3-8B as the experimental English LLM, the evaluation results demonstrate that the adapted LLM significantly enhances its capabilities in domain-specific knowledge and adaptability to safety values, while maintaining its original expertise advantages.