大模型在危机场景中如何兼顾自动翻译与紧急信息处理？这项研究为应急响应带来新思路。
arXiv:2602.13452v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly proposed for crisis preparedness and response,…
长文本翻译总在长句中崩盘？这套可恢复的LLM翻译系统设计，让失败不再重来。
arXiv:2608.09187v1 Announce Type: new Abstract: A long-form translation request can succeed at the API layer and still produce an unusable result. The…
探究语音翻译中停顿、语气词等不流畅现象的作用，为提升语音翻译模型的鲁棒性提供新视角。
arXiv:2608.02138v1 Announce Type: new Abstract: Current speech translation systems, including SpeechLLMs, are trained on cleaned text and tend to stri…
用DeepL翻译这篇TechCrunch文章，精准捕捉商业术语，快速读懂华纳兄弟收购案细节。
Learn more about Paramount's planned acquisition of Warner Bros. Discovery — a historic Hollywood megadeal valued at $111 billion — as it continues to…
翻译质量评估新范式：让AI按具体案例定制评估标准，比通用质检更精准
arXiv:2606.21559v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential in fine-grained translation quality evaluatio…
大模型在非洲低资源语言豪萨语和丰贝语上的翻译表现如何？新基准测试揭示失败模式与评估指标可靠性。
arXiv:2606.22269v1 Announce Type: cross Abstract: We investigate the translation quality of current large language models (LLMs) for English-to-Hausa …
LLM翻译文学时情感表达如何偏移？系统分析机器翻译与人工编辑中的情感变化。
arXiv:2606.10113v1 Announce Type: cross Abstract: This paper investigates whether LLM translations exhibit identifiable emotional profiles and how pos…
用强化学习优化机器翻译系统，让工具调用既精准又省钱，效果如何？arXiv最新研究给出答案。
arXiv:2606.06835v1 Announce Type: new Abstract: The performance gap across languages in LLMs is well documented, and closing it natively requires pret…
专业译者能否看穿AI翻译？一项严谨实验揭示人机文本识别真相，结果或颠覆行业认知。
arXiv:2601.15828v4 Announce Type: replace-cross Abstract: This study investigates whether professional translators without prior specialized training …
这篇论文针对机器翻译提出根据受众与意图定制内容的方法，打破传统通用翻译局限。
arXiv:2606.03259v1 Announce Type: new Abstract: Translation quality depends on purpose: the same source text demands different translations depending …
本地大模型如何兼顾翻译质量与客户数据保密？这篇论文为自由译员提供了实测基准答案
arXiv:2605.31452v1 Announce Type: new Abstract: Building on our previous work, this paper develops practical, low-barrier methods for freelance transl…
最新研究对比人类与机器翻译的去字面化假设，揭示LLM相比专用NMT系统如何产出更流畅译文
arXiv:2605.25686v1 Announce Type: new Abstract: The recent shift from dedicated NMT systems to general-purpose LLMs has reshaped machine translation, …
腾讯混元开源Hy-MT2翻译模型，同步上线「腾讯Hy翻译」小程序，邀你参加WMT26比赛赢取特设奖励。
最大提升体现在指令遵循能力上
机器翻译后编辑新思路：用错误高亮和翻译建议让修改更高效
arXiv:2605.21135v1 Announce Type: new Abstract: As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlight…
面向古籍翻译难题，提出古希腊语到现代希腊语的专用基准，对比LLM与NMT模型的微调效果。
arXiv:2605.18504v1 Announce Type: new Abstract: Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrain…
PDF翻译新突破！ForMaT数据集保留原文布局，支持15种语言对，精准处理嵌套表格等复杂结构。
arXiv:2605.15794v1 Announce Type: new Abstract: We present ForMaT (Format-Preserving Multilingual Translation), a parallel corpus of 3,956 PDFs across…
106本小说16种语言，130k段落揭示大模型文学翻译流畅性与忠实度间的微妙平衡
arXiv:2605.15282v1 Announce Type: new Abstract: Literary translation requires balancing target-language fluency with faithfulness to the source. Recen…