A Recipe for Arbitrary Text Style Transfer with Large Language Models

Emily Reif, Daphne Ippolito, Ann Yuan, Andy Coenen, Chris Callison-Burch, Jason Wei


Abstract
In this paper, we leverage large language models (LLMs) 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.’
Anthology ID:
2022.acl-short.94
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
837–848
Language:
URL:
https://aclanthology.org/2022.acl-short.94
DOI:
10.18653/v1/2022.acl-short.94
Bibkey:
Cite (ACL):
Emily Reif, Daphne Ippolito, Ann Yuan, Andy Coenen, Chris Callison-Burch, and Jason Wei. 2022. A Recipe for Arbitrary Text Style Transfer with Large Language Models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 837–848, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
A Recipe for Arbitrary Text Style Transfer with Large Language Models (Reif et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-short.94.pdf
Software:
 2022.acl-short.94.software.zip