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

• URL: http://arxiv.org/abs/2606.10113v1
• Date: Mon, 08 Jun 2026 19:46:00 GMT
• Title: Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing
• Abstract summary: We compare Margaret Atwood's Oryx and Crake with their post-edited versions and a human translation.<n>We find that MT systems introduce model-specific and statistically significant emotional fingerprints across translations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• An Investigation of Translationese in the Generations of Multilingual Large Language Models [12.692405359509259]
  It is unclear if MLLMs' generations resemble English or translationese from other languages.<n>We leverage established indicators of translated text to evaluate state-of-the-art MLLMs in five languages.<n>We examine the key features that distinguish MLLM-generated text from typical translation-related interference.
  arXiv  Detail & Related papers  (2026-08-18T05:50:36Z)
• Can an Old Dog Be Taught New Tricks? Taking LLMs Beyond Sentence Level Translation [0.0]
  We present PAT (Pragmatic Auto-Translator), a RAG-based system that pairs user-configured specifications with context from a corpus of authentic longform texts in U.S. English and Latin American Spanish.<n>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.<n>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.
  arXiv  Detail & Related papers  (2026-07-15T17:10:24Z)
• Testing the Deliteralization Hypothesis in Human and Machine Translation [23.7663178803576]
  We test the claim that translations become progressively less literal as they are drafted and revised.<n>We compare the literality of human translations and post-editions to that of two NMT systems and six LLMs across 54 language pairs.<n>We find that (i) human translations remain significantly less literal than those of all tested MT systems, though recent LLMs narrow the gap.
  arXiv  Detail & Related papers  (2026-05-25T10:40:34Z)
• Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation [57.11989521509119]
  We propose a novel agentic translation evaluation framework, centered by a reflective Core Agent that invokes specialized sub-agents.<n> Experimental results indicate the efficacy of RATE, achieving an improvement of at least 3.2 meta score compared with current metrics.
  arXiv  Detail & Related papers  (2026-01-12T09:03:42Z)
• Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation [70.43884512651668]
  We formalize Genette's (1987) theory of paratexts from literary and translation studies to introduce the task of paratextual explicitation for machine translation.<n>We construct a dataset of 560 expert-aligned paratexts from four English translations of the classical Chinese short story collection Liaozhai.<n>Our findings demonstrate the potential of paratextual explicitation in advancing machine translation beyond linguistic equivalence.
  arXiv  Detail & Related papers  (2025-09-27T16:27:36Z)
• Missing the human touch? A computational stylometry analysis of GPT-4 translations of online Chinese literature [2.3861843983281625]
  This study examines the stylistic features of large language models (LLMs)<n> Computational stylometry analysis shows that GPT-4 translations closely align with human translations in lexical, syntactic, and content features.<n>These findings offer insights into AI's impact on literary translation from a posthuman perspective.
  arXiv  Detail & Related papers  (2025-06-16T00:48:09Z)
• Lost in Literalism: How Supervised Training Shapes Translationese in LLMs [51.04435855143767]
  Large language models (LLMs) have achieved remarkable success in machine translation.<n>However, translationese, characterized by overly literal and unnatural translations, remains a persistent challenge.<n>We introduce methods to mitigate these biases, including polishing golden references and filtering unnatural training instances.
  arXiv  Detail & Related papers  (2025-03-06T12:14:45Z)
• Conditioning LLMs with Emotion in Neural Machine Translation [1.0205541448656992]
  We propose a novel pipeline that integrates emotion information extracted from a Speech Emotion Recognition (SER) model into Large Language Models (LLMs) Our experiments reveal that integrating emotion information, especially arousal, into LLM prompts leads to notable improvements in translation quality.
  arXiv  Detail & Related papers  (2024-08-06T12:49:33Z)
• (Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts [56.7988577327046]
  We introduce TransAgents, a novel multi-agent framework that simulates the roles and collaborative practices of a human translation company.<n>Our findings highlight the potential of multi-agent collaboration in enhancing translation quality, particularly for longer texts.
  arXiv  Detail & Related papers  (2024-05-20T05:55:08Z)
• Adapting Large Language Models for Document-Level Machine Translation [46.370862171452444]
  Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses on adapting LLMs for document-level machine translation (DocMT) for specific language pairs.
  arXiv  Detail & Related papers  (2024-01-12T09:29:13Z)
• Exploring Human-Like Translation Strategy with Large Language Models [93.49333173279508]
  Large language models (LLMs) have demonstrated impressive capabilities in general scenarios. This work proposes the MAPS framework, which stands for Multi-Aspect Prompting and Selection. We employ a selection mechanism based on quality estimation to filter out noisy and unhelpful knowledge.
  arXiv  Detail & Related papers  (2023-05-06T19:03:12Z)
• On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation [55.02832094101173]
  Evaluation of cross-lingual encoders is usually performed either via zero-shot cross-lingual transfer in supervised downstream tasks or via unsupervised cross-lingual similarity. This paper concerns ourselves with reference-free machine translation (MT) evaluation where we directly compare source texts to (sometimes low-quality) system translations. We systematically investigate a range of metrics based on state-of-the-art cross-lingual semantic representations obtained with pretrained M-BERT and LASER. We find that they perform poorly as semantic encoders for reference-free MT evaluation and identify their two key limitations.
  arXiv  Detail & Related papers  (2020-05-03T22:10:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.