弥合语言鸿沟：大型语言模型在机器翻译中的应用综述
Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation
AI总结：
本文综述了大型语言模型在机器翻译中的应用，探讨了提示方法、参数高效微调、合成数据生成等技术，分析了低资源翻译中的挑战与对策，以及文档级和语篇级翻译方法的发展。
摘要：
大型语言模型（LLMs）正在迅速重塑机器翻译（MT），特别是通过引入遵循指示、上下文学习和基于偏好的对齐，改变了传统监督编码器-解码器范式。本文全面概述了LLMs在MT中的应用，涵盖数据领域、语言和应用环境。我们系统分析了基于提示的方法、参数高效和全微调策略、合成数据生成、基于偏好的优化以及带有人类和弱监督反馈的强化学习。特别关注低资源翻译，探讨合成数据质量、多样性及偏好数据的作用，以及当前RLHF流程的限制。我们还回顾了混合专家模型、专注于MT的LLMs和多语言对齐的最新进展，强调可扩展性、专业化和可访问性之间的权衡。除了句子级翻译，我们还调研了新兴的文档级和语篇感知MT方法，表明大多数方法通过结构化上下文选择、后编辑或重排序扩展句子级流程，而非需要新的数据领域或架构。最后，我们讨论了基于LLM的评估，其优势和偏见，以及其与学习指标的互补作用。总体而言，本文将基于LLM的MT定位为传统MT系统的演变，其中收益越来越依赖于数据质量、偏好数据对齐和上下文利用，而非规模本身，并概述了构建稳健、包容和可控翻译系统面临的开放挑战。
英文摘要：
Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment into what has traditionally been a supervised encoder-decoder paradigm. This survey provides a comprehensive and up-to-date overview of how LLMs are being leveraged for MT across data regimes, languages, and application settings. We systematically analyze prompting-based methods, parameter-efficient and full fine-tuning strategies, synthetic data generation, preference-based optimization, and reinforcement learning with human and weakly supervised feedback. Special attention is given to low-resource translation, where we examine the roles of synthetic data quality, diversity, and preference signals, as well as the limitations of current RLHF pipelines. We further review recent advances in Mixture-of-Experts models, MT-focused LLMs, and multilingual alignment, highlighting trade-offs between scalability, specialization, and accessibility. Beyond sentence-level translation, we survey emerging document-level and discourse-aware MT methods with LLMs, showing that most approaches extend sentence-level pipelines through structured context selection, post-editing, or reranking rather than requiring fundamentally new data regimes or architectures. Finally, we discuss LLM-based evaluation, its strengths and biases, and its role alongside learned metrics. Overall, this survey positions LLM-based MT as an evolution of traditional MT systems, where gains increasingly depend on data quality, preference alignment, and context utilization rather than scale alone, and outlines open challenges for building robust, inclusive, and controllable translation systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
