ORE decouples semantic entanglement in LLM hidden states via orthogonal edit vectors and a gated non-linear head, improving batch knowledge editing performance including cross-lingual cases.
One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs
ORE decouples semantic entanglement in LLM hidden states via orthogonal edit vectors and a gated non-linear head, improving batch knowledge editing performance including cross-lingual cases.