计算机科学与探索

• 学术研究 •    下一篇

大模型微调的多领域机器翻译方法综述

陈子建, 王斯日古楞, 斯琴图   

  1. 内蒙古师范大学 计算机科学技术学院, 呼和浩特 010022

A Survey of Multi-Domain Translation Methods For Fine-Tuning Large Models

CHEN Zijian, WANG Siriguleng,  SI Qintu   

  1. College of Computer Science and Technology, Inner Mongolia University, Hohhot 010022, China

摘要: 随着机器翻译技术的快速发展,基于预训练大模型的机器翻译方法已在自然语言处理领域占据重要地位。然而,由于不同领域之间语言特征、词汇风格和表达方式的显著差异,单一预训练模型在多领域翻译任务中难以实现高效且稳定的性能。为此,本文聚焦于多领域机器翻译任务中大模型微调技术的关键问题,系统性地综述了微调技术的核心原理、主要方法及应用效果,重点分析了全参数微调、参数高效微调和提示微调三类策略的性能表现与适用场景。本文深入探讨了不同微调方法的优势与局限性,重点分析了在资源受限条件下如何通过高效微调策略平衡领域泛化能力与任务特异性,展示了参数高效微调与提示微调在资源利用效率和领域适应性方面的显著优势。通过对比分析与实验验证,进一步评估了不同微调策略在领域迁移和资源利用方面的实际效果,并通过案例分析验证了其有效性。未来的研究方向应重点关注资源的高效利用、模型的领域自适应能力,以及翻译质量和鲁棒性的提升,从而推动多领域机器翻译系统在性能与适应性方面的持续发展。

关键词: 大模型微调, 多领域机器翻译, 全参数微调, 参数高效微调, 提示微调

Abstract: With the rapid development of machine translation technology, machine translation methods based on pre-trained large models have occupied an important position in the field of natural language processing. However, due to the significant differences in language features, lexical styles and expressions between different domains, it is difficult for a single pre-trained model to achieve efficient and stable performance in multi-domain translation tasks. Therefore, this paper focuses on the key issues of large model fine-tuning technology in multi-domain machine translation tasks, systematically reviews the core principles, main methods and application effects of fine-tuning technology, and focuses on analysing the performance and applicability scenarios of the three types of strategies, namely full-parameter fine-tuning, parameter-efficient fine-tuning, and cued fine-tuning. In this paper, the advantages and limitations of different fine-tuning methods are discussed in depth, focusing on how to balance the domain generalisation ability and task specificity through efficient fine-tuning strategies under resource-constrained conditions, and demonstrating the significant advantages of parameter-efficient fine-tuning and cued fine-tuning in terms of resource utilisation efficiency and domain adaptability. The practical effects of different fine-tuning strategies in terms of domain migration and resource utilisation are further evaluated through comparative analysis and experimental validation, and their effectiveness is verified through case studies. Future research directions should focus on the efficient utilisation of resources, the domain adaptive capability of models, and the improvement of translation quality and robustness, so as to promote the continuous development of multi-domain machine translation systems in terms of performance and adaptability.

Key words: large model fine-tuning, multi-domain machine translation, full parameter fine-tuning, parameter- efficient fine-tuning, prompt-tuning