Peking U & Microsoft’s Knowledge Attribution Method Enables Editing Factual Knowledge in Pretrained Transformers Without Fine-Tuning | Synced

In the new paper Knowledge Neurons in Pretrained Transformers, a research team from Peking University and Microsoft Research introduces a knowledge attribution method that identifies the neurons that store factual knowledge in pretrained transformers and leverages these neurons to edit factual knowledge in transformers without any fine-tuning.