MOLLM formulates LLM unlearning as a three-objective optimization problem and uses a bounded unlearning loss plus a common descent direction to forget target data while preserving model utility.
Fedlf: Layer-wise fair federated learn- ing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multi-Objective Large Language Model Unlearning
MOLLM formulates LLM unlearning as a three-objective optimization problem and uses a bounded unlearning loss plus a common descent direction to forget target data while preserving model utility.