Fine-tuning Large Language Models for Domain-specific Machine Translation

no code implementations • 23 Feb 2024 • Jiawei Zheng, Hanghai Hong, Xiaoli Wang, Jingsong Su, Yonggui Liang, Shikai Wu

Second, LLMs with fine-tuning on domain-specific data often require high training costs for domain adaptation, and may weaken the zero-shot MT capabilities of LLMs due to over-specialization.

Domain Adaptation In-Context Learning +2