Steering Large Language Models with Register Analysis for Arbitrary Style Transfer
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916727964565504 |
|---|---|
| author | Yang, Xinchen Carpuat, Marine |
| author_facet | Yang, Xinchen Carpuat, Marine |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00679 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Steering Large Language Models with Register Analysis for Arbitrary Style Transfer Yang, Xinchen Carpuat, Marine Computation and Language 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. |
| title | Steering Large Language Models with Register Analysis for Arbitrary Style Transfer |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.00679 |