Text Style Transfer (TST) seeks to alter the style of text while retaining its core content. Given the constraints of limited parallel datasets for TST, we propose CoTeX, a framework that leverages large language models (LLMs) alongside chain-of-thought (CoT) prompting to facilitate TST. CoTeX distills the complex rewriting and reasoning capabilities of LLMs into more streamlined models capable of working with both non-parallel and parallel data. Through experimentation across four TST datasets, CoTeX is shown to surpass traditional supervised fine-tuning and knowledge distillation methods, particularly in low-resource settings. We conduct a comprehensive evaluation, comparing CoTeX against current unsupervised, supervised, in-context learning (ICL) techniques, and instruction-tuned LLMs. Furthermore, CoTeX distinguishes itself by offering transparent explanations for its style transfer process.
@article{arxiv.2403.01106,
title = {Distilling Text Style Transfer With Self-Explanation From LLMs},
author = {Chiyu Zhang and Honglong Cai and Yuezhang and Li and Yuexin Wu and Le Hou and Muhammad Abdul-Mageed},
journal= {arXiv preprint arXiv:2403.01106},
year = {2024}
}