# 研究：读者认为AI文学翻译"还行"，但仍偏爱人工翻译

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-24 08:00
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmr3b2evp026isly0dt6veetv
- 原文链接：https://arxiv.org/abs/2606.26040

## AI 摘要

一项研究对比了基于智能体大语言模型的机器翻译（MT）与人工翻译（HT）在文学作品中的读者体验。15名读者评估了15部近期从法语、波兰语和日语译成英语的小说节选（每部约8000词）。在沉浸式阅读（30次比较）和精读（772次片段对比）中，读者认为MT“还行”，但更偏好HT（节选19/30偏好HT，片段522/772），因其更易读、清晰且沉浸。MT质量波动更大。读者无法可靠区分两者（17/30猜对），且倾向于相信是人工翻译的版本。自动评测指标（包括LLM作为评判者）无法复现读者偏好。研究发布了LAIT数据集（含1000条读者评论、2000条偏好评分、7200条片段级标注）。

## 正文

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.