Fine-tuning Large Language Models for Domain-specific Machine Translation
This addresses domain-specific machine translation for users needing accurate translations in specialized fields, but it is incremental as it builds on existing fine-tuning and prompting techniques.
The paper tackled the problem of large language models (LLMs) underperforming in domain-specific machine translation due to lack of domain knowledge, and proposed DragFT, a fine-tuning framework that achieved significant performance boosts over models like GPT-3.5 and GPT-4o on three domain-specific datasets.
Large language models (LLMs) have shown great potential in domain-specific machine translation (MT). However, one major issue is that LLMs pre-trained on general domain corpus might not generalize well to specific domains due to the lack of domain-specific knowledge. To address this issue, this paper focuses on enhancing the domain-specific MT capability of LLMs, by providing high-quality training datasets and proposing a novel fine-tuning framework denoted by DragFT. DragFT augments LLMs via three techniques: (i) Dictionary-enhanced prompting integrates dictionary information into prompts to improve the translation of domain-specific terminology.; (ii) RAG-based few-shot example selection provides high-quality examples that simulate both the domain and style characteristics; (iii) Fine-tuning with few-shot examples further enhances performance when using in-domain examples. We deploy DragFT on three well-known LLM backbones with 13B training parameters to validate its effectiveness. The results on three domain-specific datasets show that DragFT achieves a significant performance boost and shows superior performance compared to advanced models such as GPT-3.5 and GPT-4o. The drastic performance improvement of DragFT over existing LLMs can be attributed to incorporating relevant knowledge while mitigating noise.