LMs store facts in task-specific parameter subsets, shown by inconsistent emergence across tasks during training and distinct localized parameters for the same fact.
Intrinsic Test of Unlearning Using Parametric Knowledge Traces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
EMBER augments existing erasure methods by precisely removing concept features from embeddings via sparse matrix factorization, cutting relearning recovery to 35% on Llama-3.1-8B from 70-76%.
citing papers explorer
-
LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
LMs store facts in task-specific parameter subsets, shown by inconsistent emergence across tasks during training and distinct localized parameters for the same fact.
-
Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings
EMBER augments existing erasure methods by precisely removing concept features from embeddings via sparse matrix factorization, cutting relearning recovery to 35% on Llama-3.1-8B from 70-76%.