Distilling Text Style Transfer With Self-Explanation From LLMs
Zhang, Chiyu, Cai, Honglong, Yuezhang, null, Li, null, Wu, Yuexin, Hou, Le, Abdul-Mageed, Muhammad
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
May-4-2024
- Country:
- North America
- Dominican Republic (0.04)
- United States
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > Los Angeles County
- Long Beach (0.04)
- New Mexico > Santa Fe County
- Canada
- Ontario > Toronto (0.05)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Europe
- Switzerland (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia
- China > Hong Kong (0.04)
- Singapore (0.04)
- Macao (0.04)
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- India > Maharashtra
- Mumbai (0.04)
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- North America
- Genre:
- Research Report (1.00)
- Technology: