Mass-editing Memory In A Transformer

Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, David Bau. Arxiv 2022 – 49 citations

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

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