Unilogit unlearns text from LLMs by setting the target token probability to 1/|V| and distilling from the current model, reporting stronger forgetting at comparable retained utility than NPO and UnDIAL.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation
Unilogit unlearns text from LLMs by setting the target token probability to 1/|V| and distilling from the current model, reporting stronger forgetting at comparable retained utility than NPO and UnDIAL.