A Recipe For Arbitrary Text Style Transfer with Large Language Models
This addresses the problem of flexible text style transfer for users needing to modify text styles without extensive training data, though it is incremental as it builds on existing large language models.
The paper tackles text style transfer by introducing augmented zero-shot learning, a prompting method that uses large language models to rewrite sentences based on natural language instructions without fine-tuning, achieving promising results on both standard tasks like sentiment and arbitrary transformations such as making text melodramatic.
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."