research
∙
08/17/2023
Linearity of Relation Decoding in Transformer Language Models
Much of the knowledge encoded in transformer language models (LMs) may b...
share
research
∙
10/13/2022
Mass-Editing Memory in a Transformer
Recent work has shown exciting promise in updating large language models...
research
∙
07/28/2022
Exploiting and Defending Against the Approximate Linearity of Apple's NeuralHash
Perceptual hashes map images with identical semantic content to the same...
research
∙
02/10/2022
Locating and Editing Factual Knowledge in GPT
We investigate the mechanisms underlying factual knowledge recall in aut...
research
∙
02/18/2020