This paper proposes a novel method for Text Style Transfer (TST) based on parameter-efficient fine-tuning of Large Language Models (LLMs). Addressing the scarcity of parallel corpora that map between styles, the study employs roundtrip translation to synthesize such parallel datasets from monolingual corpora. This approach creates 'neutralized' text devoid of stylistic attributes, essentially creating a shared input style at training-time and inference-time. Experimental results demonstrate consistent superiority of this method over zero-shot prompting and fewshot ICL techniques measured by BLEU scores and style accuracy scores across four investigated domains. Furthermore, the integration of retrieval-augmented generation (RAG) for terminology and name knowledge enhances robustness and stylistic consistency.

翻译：本文提出了一种基于参数高效微调大语言模型的文本风格迁移新方法。针对风格映射平行语料稀缺的问题，本研究采用往返翻译技术，从单语语料库中合成此类平行数据集。该方法生成不具风格属性的“中性化”文本，本质上在训练时和推理时创建了共享的输入风格。实验结果表明，在四个研究领域中，该方法在BLEU分数和风格准确度分数上均持续优于零样本提示和少样本上下文学习技术。此外，通过集成检索增强生成技术以获取术语和专名知识，进一步增强了方法的鲁棒性与风格一致性。