Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.
URL https://aclanthology.org/2025.acl-long
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.