We introduce mEdIT, a multi-lingual extension to CoEdIT -- the recent state-of-the-art text editing models for writing assistance. mEdIT models are trained by fine-tuning multi-lingual large, pre-trained language models (LLMs) via instruction tuning. They are designed to take instructions from the user specifying the attributes of the desired text in the form of natural language instructions, such as Grammatik korrigieren (German) or Parafrasee la oraci\'on (Spanish). We build mEdIT by curating data from multiple publicly available human-annotated text editing datasets for three text editing tasks (Grammatical Error Correction (GEC), Text Simplification, and Paraphrasing) across diverse languages belonging to six different language families. We detail the design and training of mEdIT models and demonstrate their strong performance on many multi-lingual text editing benchmarks against other multilingual LLMs. We also find that mEdIT generalizes effectively to new languages over multilingual baselines. We publicly release our data, code, and trained models at https://github.com/vipulraheja/medit.

翻译：我们提出了mEdIT，这是CoEdIT（近期在写作辅助中表现最优的文本编辑模型）的多语言扩展。mEdIT模型通过对多语言大型预训练语言模型（LLMs）进行指令调优微调而来。其设计旨在接收用户以自然语言指令形式指定的目标文本属性，例如"Grammatik korrigieren"（德语）或"Parafrasee la oración"（西班牙语）。我们通过整合来自多个公开人工标注文本编辑数据集的数据构建mEdIT，这些数据涵盖六种不同语系语言的三个文本编辑任务（语法错误纠正、文本简化与释义）。本文详细阐述了mEdIT模型的设计与训练过程，并展示了其在多语言文本编辑基准测试中相较于其他多语言LLMs的优异性能。研究还发现，相较于多语言基线模型，mEdIT能有效泛化至新语言。我们已在https://github.com/vipulraheja/medit 公开发布了数据、代码与训练模型。