Abstract
This paper addresses the challenge in long-text style transfer using zero-shot learning of large language models (LLMs), proposing a hierarchical framework that combines sentence-level stylistic adaptation with paragraph-level structural coherence. We argue that in the process of effective paragraph-style transfer, to preserve the consistency of original syntactic and semantic information, it is essential to perform style transfer not only at the sentence level but also to incorporate paragraph-level semantic considerations, while ensuring structural coherence across inter-sentential relationships. Our proposed framework, ZeroStylus, operates through two systematic phases: hierarchical template acquisition from reference texts and template-guided generation with multi-granular matching. The framework dynamically constructs sentence and paragraph template repositories, enabling context-aware transformations while preserving inter-sentence logical relationships. Experimental evaluations demonstrate significant improvements over baseline methods, with structured rewriting achieving 6.90 average score compared to 6.70 for direct prompting approaches in tri-axial metrics assessing style consistency, content preservation, and expression quality. Ablation studies validate the necessity of both template hierarchies during style transfer, showing higher content preservation win rate against sentence-only approaches through paragraph-level structural encoding, as well as direct prompting method through sentence-level pattern extraction and matching. The results establish new capabilities for coherent long-text style transfer without requiring parallel corpora or LLM fine-tuning.
Abstract (translated)
本文探讨了使用大型语言模型（LLM）的零样本学习在长文本风格转换中的挑战，并提出了一种分层框架，该框架结合了句子级别的风格适应与段落级别的结构一致性。我们主张，在进行有效的段落级风格转换过程中，为了保持原始句法和语义信息的一致性，仅在句子级别上执行风格转移是不够的，还必须纳入段落级别的语义考虑，并确保跨句子关系中的结构连贯性。 我们的框架ZeroStylus通过两个系统阶段运作：从参考文本中获得分层模板以及使用多粒度匹配进行模板引导生成。该框架动态构建了句级和段落级模板库，使得在保持句子间逻辑关系的同时能够进行上下文感知的转换。 实验评估显示，在评估风格一致性、内容保留和表达质量三个维度上的三轴向指标中，结构化重写方法比直接提示方法平均得分高出0.2分（6.90对6.70），超过了基线方法。消融研究验证了在风格转移过程中使用模板层次结构的必要性：通过段落级别的结构性编码，在内容保留胜率上超越仅处理句子的方法；通过句级模式提取和匹配，也优于直接提示法。 这些结果为无需平行语料库或LLM微调的一致长文本风格转换建立了新的能力。
URL
https://arxiv.org/abs/2505.07888
