Large sequence to sequence models for tasks such as Neural Machine
Translation (NMT) are usually trained over hundreds of millions of samples.
However, training is just the origin of a model's life-cycle. Real-world
deployments of models require further behavioral adaptations as new
re
介绍了一种基于 Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC) 的模型编辑方法,具备内存高、编辑表达能力强的特点,能够高效地处理基于问答、事实核查和对话生成的 3 种具有挑战性的语言模型编辑问题。