ResearchTasksAbliteration detectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedWild audit (held-out, leave-one-family-out)Combined z-sum90Detection Rate5Jul 3, 2026Wild audit (in-sample)Combined z-sum95AUROC4Jul 3, 2026