Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.
Jiahao Yu, Xingwei Lin, Zheng Yu, and Xinyu Xing
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
-
Exclusive Unlearning
Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.