AI 中文总结
探讨能否让大语言模型超越逐句翻译范式，提出基于RAG的PAT系统，通过与语料库结合让大语言模型进行全文翻译生成草稿，经评估发现其能朝重新表述发展，但提升重新表述有效性仍需更多工作，还讨论了相关设计与评估等要点。
AI 中文摘要
自动翻译系统大多将翻译视为逐句行为。本文探讨能否通过基于语料库的全文翻译让大语言模型超越该范式。我们提出了PAT（实用自动翻译器），这是一个基于RAG的系统，将用户配置的规范与来自美国英语和拉丁美洲西班牙语真实长篇文本可比语料库的上下文配对，将检索到的段落、章节和文档级示例传递给大语言模型进行全文生成。目标是为专业验证生成翻译草稿。我们使用定制的MQM类型对三个项目中关于生成式人工智能的论文的六种自动翻译进行了评估，由两名训练有素的评估人员从美国英语翻译成拉丁美洲和墨西哥西班牙语。结果表明，有限的提示不会产生有意义的重新表述，规范和基于语料库的翻译有时会有实质性的重新表述，但并非总是有效。我们发现大语言模型可以朝着重新表述的方向发展，远离逐句范式，但仍需更多工作来提高这些重新表述的有效性。本文讨论了与自动翻译系统设计、语料库构建以及翻译质量评估方法和结果相关的考虑因素。
英文摘要
Automatic translation systems, from CAT tools to MT, overwhelmingly treat translation as a sentence-by-sentence act. This paper asks whether LLMs can be moved beyond that paradigm through whole-document, corpus-informed translation. We present PAT (Pragmatic Auto-Translator), a RAG-based system that pairs user-configured specifications with context from a comparable corpus of authentic longform texts in U.S. English and Latin American Spanish, passing retrieved paragraph-, section-, and document-level examples to an LLM for whole-document generation. The goal is draft translation for professional verification: target texts reformulated to fit their Spanish-language context, where discourse organization, rhetorical style, and pragmatic norms differ meaningfully from English. We evaluated six automatic translations of essays on generative AI across three projects using a customized MQM typology, assessed by two trained evaluators working from U.S. English into LATAM and Mexican Spanish. Results show that a limited prompt produced no meaningful reformulation, and specifications and corpus-informed translations at times showed substantial reformulation, though not always to effect. We find that LLMs can be moved toward reformulation and away from the sentence-by-sentence paradigm, though more work is needed to improve the effectiveness of those reformulations. In this paper, we discuss considerations related to automatic translation system design, corpus construction, and translation quality evaluation methodology and results.
CommentsAccepted for publication in HCI International 2026, Late Breaking Papers Proceedings, Springer LNCS
