监督微调导致大模型翻译过于字面化，研究提出优化方法提升翻译自然度。
Lost in Literalism: How Supervised Training Shapes Translationese in LLMs
- 通过分析监督微调过程，揭示翻译腔的成因。
- 优化参考译文与过滤异常训练样本，显著减少字面化错误。
- 适合关注翻译质量提升与模型训练优化的研究者。
大语言模型在机器翻译中取得显著成功，但在多语言场景下仍普遍存在翻译腔问题，表现为过度字面化和不自然的表达。尽管模型预训练阶段接触过大量自然语料，其在监督微调（SFT）过程中引入的偏差仍导致生成不自然的翻译。本文系统评估了翻译腔在大模型翻译中的普遍性，并探究其在监督训练中的根源。提出通过润色高质量参考译文、过滤不自然训练样本等方法缓解该问题。实验表明，这些策略能有效降低翻译腔，提升翻译流畅性，经人工评估与自动指标验证。研究强调需在训练阶段进行针对性调整，以实现更流畅、符合目标语言习惯的翻译输出。数据与代码已开源：https://github.com/yafuly/LLM_Translationese。
原文摘要 · Abstract (English)
Large language models (LLMs) have achieved remarkable success in machine translation, demonstrating impressive performance across diverse languages. However, translationese, characterized by overly literal and unnatural translations, remains a persistent challenge in LLM-based translation systems. Despite their pre-training on vast corpora of natural utterances, LLMs exhibit translationese errors and generate unexpected unnatural translations, stemming from biases introduced during supervised fine-tuning (SFT). In this work, we systematically evaluate the prevalence of translationese in LLM-generated translations and investigate its roots during supervised training. We introduce methods to mitigate these biases, including polishing golden references and filtering unnatural training instances. Empirical evaluations demonstrate that these approaches significantly reduce translationese while improving translation naturalness, validated by human evaluations and automatic metrics. Our findings highlight the need for training-aware adjustments to optimize LLM translation outputs, paving the way for more fluent and target-language-consistent translations. We release the data and code at https://github.com/yafuly/LLM_Translationese.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。