mEdIT：通过指令微调实现多语言文本编辑
mEdIT: Multilingual Text Editing via Instruction Tuning
AI总结：
本研究提出多语言文本编辑模型mEdIT，通过指令微调多语言预训练大模型，覆盖六大语系三类编辑任务，在多基准上性能优于现有多语言大模型，且对新语言泛化性更好，相关资源已公开。
摘要：
我们推出mEdIT，它是近期用于写作辅助的前沿文本编辑模型CoEdIT的多语言扩展版本。mEdIT模型通过指令微调的方式对多语言大型预训练语言模型（LLMs）进行微调训练，设计上支持接收用户以自然语言指令形式指定目标文本属性的需求，例如德语的“Grammatik korrigieren（纠正语法）”或西班牙语的“Parafrasee la oración（改写句子）”。我们通过整理多个公开的人工标注文本编辑数据集构建了mEdIT，覆盖六大语系的不同语言，支持三类文本编辑任务：语法错误纠正（GEC）、文本简化和释义改写。我们详细阐述了mEdIT模型的设计与训练过程，并在多个多语言文本编辑基准上验证了其相较于其他多语言LLMs的优异性能。我们还发现，相比多语言基线模型，mEdIT能更有效地泛化到新语言上。我们已在https://github.com/vipulraheja/medit 公开发布了数据集、代码和训练好的模型。
英文摘要：
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 oración (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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
