BriefGPT.xyz
Jun, 2022
使用大型多语言模型探索跨语言文本风格转移
Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models
HTML
PDF
Daniil Moskovskiy, Daryna Dementieva, Alexander Panchenko
TL;DR
研究多语言和跨语言毒化以及大型多语言模型在该环境中的行为,探讨使大型语言模型能够在给定语言中执行解毒操作而无需直接微调的方法; 实验证明,多语言模型能够执行多语言风格转换,但是模型无法执行跨语言解毒,所以对特定语言进行直接微调是不可避免的。
Abstract
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 i
→