DF-MCQ flattens a model's predictions over multiple-choice questions to make it refuse target-person queries, and the paper's probing tests suggest this removes knowledge rather than merely obfuscating it.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?
DF-MCQ flattens a model's predictions over multiple-choice questions to make it refuse target-person queries, and the paper's probing tests suggest this removes knowledge rather than merely obfuscating it.