AI RESEARCH
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
arXiv CS.LG
•
ArXi:2605.30514v1 Announce Type: new Machine unlearning evaluation is structurally skewed: Why-type questions, which probe causal and relational knowledge, comprise less than 0.06% of CounterFact, 0.6% of ZSRE, and less than 1.3% of TOFU, MUSE, and WMDP-Cyber. This near-zero representation means that methods that fail on causal knowledge can score highly in aggregate, and this failure is undetectable without balanced evaluation.