人工智能对文学文本的翻译“还行”，但读者仍然更偏好人工翻译。

摘要

文学作品的人工智能翻译日益普遍。尽管内容可能得到恰当呈现，但我们对读者在沉浸感和文学效果方面的体验知之甚少——这些方面是自动机器翻译指标或针对流畅度和充分性的人工评估难以捕捉的。我们请15位热衷阅读的读者，将近期出版的法语、波兰语和日语三部小说的最新人类翻译（HT）与基于智能大语言模型（LLM）流程生成的机器翻译（MT）进行对比，这些小说被译成了英语。读者对约8000词的摘录进行了两种条件下的评估：对整篇摘录的沉浸式阅读（30次对比）以及对386个对齐的HT-MT片段对的仔细阅读（772次对比），每本书由两位读者参与，且呈现顺序交替进行。总体而言，读者认为MT“尚可”，但更偏好HT（在摘录层面为19/30，稍显优势；在片段层面为522/772，更为明显），因为HT更易读、清晰且具有沉浸感。读者的标注显示，MT在一本书内的质量波动比HT更大。关键在于，读者无法可靠地区分两者（17/30次猜对），且倾向于相信自己以为是人工翻译的版本。自动评估指标（包括以LLM为裁判的方法）无法反映读者偏好，反而更偏向MT。我们发布了LAIT（文学人工智能翻译）数据集，这是一个以读者为中心的评估数据集，包含1000条读者评论、2000条判断与偏好评分，以及7200个片段级标注，同时提供了我们的评估协议和支持性界面。

English

AI translation of literary works is increasingly common. While the content may be rendered adequately, we do not know enough about how readers experience it in terms of immersiveness and literary effect, aspects poorly captured by automatic machine translation metrics or human evaluation targeting fluency and adequacy. We ask 15 avid readers to compare recently published human translations (HT) to machine translations (MT) generated with an agentic large language model (LLM)-based pipeline, for 15 recent novels in French, Polish, and Japanese and translated into English. Readers evaluated approximately 8K-word excerpts in two conditions: immersive reading of the whole excerpt (30 comparisons) and close reading of 386 aligned HT-MT chunk pairs (772 comparisons), with two readers per book and in alternating order of presentation. Overall, readers find MT "fine", but prefer HT (slightly at excerpt-level 19/30, more clearly at chunk-level 522/772) for its ease, clarity, and immersive nature. Readers' highlights show that MT's quality varies more within one book than HT's does. Crucially, readers cannot reliably tell the two apart (17/30 guess correctly) and tend to prefer the version they believe to be human. Automatic metrics, including LLM-as-a-judge approaches, fail to recover reader preferences and favor MT. We release LAIT (Literary AI Translation), a reader-centered evaluation dataset with 1K reader comments, 2K judgments and preference ratings, and 7.2K span-level annotations, along with our evaluation protocol and supporting interface.