论文标题
使用大型多语言模型探索跨语性文本样式转移
Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models
论文作者
论文摘要
排毒是以礼貌风格生成文本的任务，同时保留原始有毒文本的含义和流利性。现有的排毒方法旨在用一种精确的语言工作。这项工作研究了多语言和跨语性排毒以及在这种情况下的大型多语言模型的行为。与以前的作品不同，我们旨在使大型语言模型能够执行排毒，而无需直接以给定语言进行微调。实验表明，多语言模型能够执行多语言样式转移。但是，模型无法执行跨语性排毒，并且对精确语言进行直接微调是不可避免的。
Detoxification is a task of generating text in polite style while preserving meaning and fluency of the original toxic text. Existing detoxification methods are designed to work in one exact language. This work investigates multilingual and cross-lingual detoxification and the behavior of large multilingual models like in this setting. Unlike previous works we aim to make large language models able to perform detoxification without direct fine-tuning in given language. Experiments show that multilingual models are capable of performing multilingual style transfer. However, models are not able to perform cross-lingual detoxification and direct fine-tuning on exact language is inevitable.
