A Recipe For Arbitrary Text Style Transfer with Large Language Models

2021/09/08 by Reif, Emily, Ippolito, Daphne, Yuan, Ann +3 · 6 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2109.03910

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."

Cited by

• Examining the Usage of Generative AI Models in Student Learning Activities for Software Programming
• Designing Beyond Language: Sociotechnical Barriers in AI Health Technologies for Limited English Proficiency
• LLM-Friendly Knowledge Representation for Customer Support
• From Detection to Mitigation: Addressing Gender Bias in Chinese Texts via Efficient Tuning and Voting-Based Rebalancing
• Finding your MUSE: Mining Unexpected Solutions Engine
• Retrieval-Augmented Review Generation for Poisoning Recommender Systems

Related

• Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models
• Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings
• Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mapping
• Steering Large Language Models with Register Analysis for Arbitrary Style Transfer
• Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles