Decoder-only LLMs have shown impressive performance in MT due to their ability to learn from extensive datasets and generate high-quality translations. However, LLMs often struggle with the nuances and style required for organisation-specific translation. In this study, we explore the effectiveness of fine-tuning Large Language Models (LLMs), particularly Llama 3 8B Instruct, leveraging translation memories (TMs), as a valuable resource to enhance accuracy and efficiency. We investigate the impact of fine-tuning the Llama 3 model using TMs from a specific organisation in the software sector. Our experiments cover five translation directions across languages of varying resource levels (English to Brazilian Portuguese, Czech, German, Finnish, and Korean). We analyse diverse sizes of training datasets (1k to 207k segments) to evaluate their influence on translation quality. We fine-tune separate models for each training set and evaluate their performance based on automatic metrics, BLEU, chrF++, TER, and COMET. Our findings reveal improvement in translation performance with larger datasets across all metrics. On average, BLEU and COMET scores increase by 13 and 25 points, respectively, on the largest training set against the baseline model. Notably, there is a performance deterioration in comparison with the baseline model when fine-tuning on only 1k and 2k examples; however, we observe a substantial improvement as the training dataset size increases. The study highlights the potential of integrating TMs with LLMs to create bespoke translation models tailored to the specific needs of businesses, thus enhancing translation quality and reducing turn-around times. This approach offers a valuable insight for organisations seeking to leverage TMs and LLMs for optimal translation outcomes, especially in narrower domains.

翻译：仅解码器架构的大型语言模型（LLM）因其能够从海量数据中学习并生成高质量译文，在机器翻译领域展现出卓越性能。然而，这类模型往往难以掌握特定组织所需的翻译细节与风格特征。本研究探讨了利用翻译记忆库（TM）作为增强准确性与效率的重要资源，对大型语言模型（特别是Llama 3 8B Instruct）进行微调的有效性。我们通过在软件行业特定组织的翻译记忆库上微调Llama 3模型，系统考察了其影响。实验涵盖五种不同资源水平语言对的翻译方向（英语到巴西葡萄牙语、捷克语、德语、芬兰语和韩语），通过分析不同规模的训练数据集（1k至207k个句段）评估其对翻译质量的影响。我们为每个训练集分别微调模型，并基于BLEU、chrF++、TER和COMET等自动指标评估性能。研究结果表明：在所有指标上，更大规模数据集均能提升翻译性能。使用最大训练集时，BLEU和COMET分数相较基线模型平均分别提升13分和25分。值得注意的是，仅使用1k和2k样本微调时会出现性能退化，但随着训练数据规模扩大，我们观察到显著改善。本研究揭示了将翻译记忆库与大型语言模型相结合，为企业定制专属翻译模型的潜力，从而提升翻译质量并缩短交付周期。该方法为寻求利用翻译记忆库和大型语言模型实现最优翻译效果的组织提供了重要参考，尤其在专业细分领域更具应用价值。