CURaTE performs continual unlearning in LLMs in real time by using sentence embeddings to detect and refuse forget requests without changing model parameters, achieving effective forgetting and perfect knowledge preservation.
Ruiqi Zhang, Licong Lin, Yu Bai, and Song Mei
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
-
CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge
CURaTE performs continual unlearning in LLMs in real time by using sentence embeddings to detect and refuse forget requests without changing model parameters, achieving effective forgetting and perfect knowledge preservation.