Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing

Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing

基于大语言模型的文学翻译情感分析：机器翻译与译后编辑中的系统性偏移

Abstract: This paper investigates whether LLM translations exhibit identifiable emotional profiles and how post-editing reshapes them toward human-like norms. We compare LLM translations of Margaret Atwood’s Oryx and Crake with their post-edited versions and a human translation, using a large-scale corpus of contemporary Italian science-fiction as a baseline. We examine emotion through lexicon-based and multilingual modeling, conducting a fine-grained analysis of emotional variation across systems. We find that MT systems introduce model-specific and statistically significant emotional fingerprints across translations, leading to a limited preservation of an author’s voice.

摘要： 本文旨在探讨大语言模型（LLM）的翻译是否表现出可识别的情感特征，以及译后编辑（Post-editing）如何将其重塑为更符合人类习惯的规范。我们以当代意大利科幻小说的大规模语料库为基准，对比了玛格丽特·阿特伍德（Margaret Atwood）作品《羚羊与秧鸡》（Oryx and Crake）的LLM翻译版本、译后编辑版本以及人工翻译版本。通过基于词汇和多语言建模的方法，我们对不同系统间的情感差异进行了细致分析。研究发现，机器翻译系统在翻译过程中会引入模型特有的、具有统计学意义的情感“指纹”，导致作者的个人风格难以得到充分保留。

---

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) 学科分类： 计算与语言 (cs.CL)；人工智能 (cs.AI)

Authors: Antonio Castaldo, Johanna Monti, Sheila Castilho 作者： Antonio Castaldo, Johanna Monti, Sheila Castilho

Submission Date: 8 Jun 2026 提交日期： 2026年6月8日