Steering Large Language Models with Register Analysis for Arbitrary Style Transfer

TL;DR

This paper introduces a register analysis-based prompting method to improve arbitrary style transfer in large language models, enabling more effective and meaning-preserving text rewriting guided by style exemplars.

Contribution

The paper presents a novel prompting technique using register analysis to better control style transfer in LLMs, addressing a key challenge in example-based style rewriting.

Findings

Enhanced style transfer strength compared to existing methods

Better preservation of original meaning during style transfer

Effective guidance of LLMs with register-based prompts

Abstract

Large Language Models (LLMs) have demonstrated strong capabilities in rewriting text across various styles. However, effectively leveraging this ability for example-based arbitrary style transfer, where an input text is rewritten to match the style of a given exemplar, remains an open challenge. A key question is how to describe the style of the exemplar to guide LLMs toward high-quality rewrites. In this work, we propose a prompting method based on register analysis to guide LLMs to perform this task. Empirical evaluations across multiple style transfer tasks show that our prompting approach enhances style transfer strength while preserving meaning more effectively than existing prompting strategies.