KNE selects top-attribution neurons across all layers and updates only those weights, claiming improved knowledge editing accuracy on Llama-2-7B and GPT-J-6B.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble
KNE selects top-attribution neurons across all layers and updates only those weights, claiming improved knowledge editing accuracy on Llama-2-7B and GPT-J-6B.