178 citations · 247 across the 5 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.CL2022★ 56 cited
Mass-Editing Memory in a Transformer
Kevin Meng, Arnab Sen Sharma, Alex Andonian +2
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 o…
cs.CR2022
Exploiting and Defending Against the Approximate Linearity of Apple's NeuralHash
Jagdeep Singh Bhatia, Kevin Meng
Perceptual hashes map images with identical semantic content to the same -bit hash value, while mapping semantically-different images to different hashes. These algorithms carry…
cs.CL2022★ 178 cited
Locating and Editing Factual Associations in GPT
Kevin Meng, David Bau, Alex Andonian +1
We analyze the storage and recall of factual associations in autoregressive transformer language models, finding evidence that these associations correspond to localized, directly-…