Fixed golden layers for knowledge editing in LLMs can be identified via gradient attribution and generalize across queries and datasets.
Revisit, extend, and enhance hessian-free influence functions.CoRR, abs/2405.17490
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
DMin uses gradient compression to scalably estimate training data influence in billion-parameter diffusion models.
citing papers explorer
-
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
Fixed golden layers for knowledge editing in LLMs can be identified via gradient attribution and generalize across queries and datasets.
-
DMin: Scalable Training Data Influence Estimation for Diffusion Models
DMin uses gradient compression to scalably estimate training data influence in billion-parameter diffusion models.