Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning
Alves, Duarte M., Guerreiro, Nuno M., Alves, João, Pombal, José, Rei, Ricardo, de Souza, José G. C., Colombo, Pierre, Martins, André F. T.
–arXiv.org Artificial Intelligence
Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often require extra post-processing due to overgeneration. Alternatives such as finetuning on translation instructions are computationally expensive and may weaken in-context learning capabilities, due to overspecialization. In this paper, we provide a closer look at this problem. We start by showing that adapter-based finetuning with LoRA matches the performance of traditional finetuning while reducing the number of training parameters by a factor of 50. This method also outperforms few-shot prompting and eliminates the need for post-processing or in-context examples. However, we show that finetuning generally degrades few-shot performance, hindering adaptation capabilities. Finally, to obtain the best of both worlds, we propose a simple approach that incorporates few-shot examples during finetuning. Experiments on 10 language pairs show that our proposed approach recovers the original few-shot capabilities while keeping the added benefits of finetuning.
arXiv.org Artificial Intelligence
Oct-20-2023
- Country:
- North America > United States
- Pennsylvania (0.04)
- New York > New York County
- New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Europe
- United Kingdom (0.04)
- Romania > Sud - Muntenia Development Region
- Giurgiu County > Giurgiu (0.04)
- Portugal > Lisbon
- Lisbon (0.14)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Italy > Tuscany
- Florence (0.04)
- France > Île-de-France
- Asia > Middle East
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Republic of Türkiye > Istanbul Province
- Istanbul (0.04)
- UAE > Abu Dhabi Emirate
- North America > United States
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Health & Medicine (0.47)
- Technology: