Mass-editing Memory In A Transformer

Meng Kevin, Sharma Arnab Sen, Andonian Alex, Belinkov Yonatan, Bau David. Arxiv 2022

[Paper] [Code]    
GPT Has Code Model Architecture Pretraining Methods Transformer

Recent work has shown exciting promise in updating large language models with new memories, so as to replace obsolete information or add specialized knowledge. However, this line of work is predominantly limited to updating single associations. We develop MEMIT, a method for directly updating a language model with many memories, demonstrating experimentally that it can scale up to thousands of associations for GPT-J (6B) and GPT-NeoX (20B), exceeding prior work by orders of magnitude. Our code and data are at https://memit.baulab.info.

Similar Work