English

A Recipe For Arbitrary Text Style Transfer with Large Language Models

Computation and Language 2022-04-01 v4

Abstract

In this paper, we leverage large language models (LMs) to perform zero-shot text style transfer. We present a prompting method that we call augmented zero-shot learning, which frames style transfer as a sentence rewriting task and requires only a natural language instruction, without model fine-tuning or exemplars in the target style. Augmented zero-shot learning is simple and demonstrates promising results not just on standard style transfer tasks such as sentiment, but also on arbitrary transformations such as "make this melodramatic" or "insert a metaphor."

Keywords

Cite

@article{arxiv.2109.03910,
  title  = {A Recipe For Arbitrary Text Style Transfer with Large Language Models},
  author = {Emily Reif and Daphne Ippolito and Ann Yuan and Andy Coenen and Chris Callison-Burch and Jason Wei},
  journal= {arXiv preprint arXiv:2109.03910},
  year   = {2022}
}
R2 v1 2026-06-24T05:48:19.722Z