Abstract
Large Language Models (LLMs) are emerging as dominant forces for textual style transfer. However, for arbitrary style transfer, LLMs face two key challenges: (1) considerable reliance on manually-constructed prompts and (2) rigid stylistic biases inherent in LLMs. In this paper, we propose a novel Synthesize-then-Decode (SynDec) approach, which automatically synthesizes high-quality prompts and amplifies their roles during decoding process. Specifically, our approach synthesizes prompts by selecting representative few-shot samples, conducting a four-dimensional style analysis, and reranking the candidates. At LLM decoding stage, the TST effect is amplified by maximizing the contrast in output probabilities between scenarios with and without the synthesized prompt, as well as between prompts and negative samples. We conduct extensive experiments and the results show that SynDec outperforms existing state-of-the-art LLM-based methods on five out of six benchmarks (e.g., achieving up to a 9\% increase in accuracy for modern-to-Elizabethan English transfer). Detailed ablation studies further validate the effectiveness of SynDec.
Abstract (translated)
大型语言模型（LLM）正在成为文本风格转换的主导力量。然而，对于任意风格的文本转换，LLM面临着两个关键挑战：(1) 对于手动构建提示词的高度依赖；(2) LLM本身固有的僵化风格偏见。在这篇论文中，我们提出了一种新颖的“合成-解码”（SynDec）方法，该方法能够自动生成高质量的提示词，并在解码过程中增强它们的作用。具体而言，我们的方法通过选择代表性的小样本、进行四维风格分析以及重新排名候选者来合成提示词。在LLM解码阶段，我们通过最大化有无合成提示和正负样本之间输出概率的对比差异来放大TST（文本样式转换）效应。我们进行了广泛的实验，并且结果显示SynDec在六个基准中的五个上优于现有的最先进的基于LLM的方法（例如，在现代英语到伊丽莎白时代英语的风格转换中，准确率提高了高达9%）。详细的消融研究进一步验证了SynDec的有效性。
URL
https://arxiv.org/abs/2505.12821
