ResearchTasksJailbreak defense and Utility evaluationJailbreak defense and Utility evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedImplicit risk dataset ManagementDPP-MENTOR0.8Jailbreak Success Rate (JSR)30Jun 4, 2026Implicit risk dataset FinanceMENTOR0.4Jailbreak Success Rate (JSR)30Jun 4, 2026Implicit risk dataset EducationDPP-MENTOR6.4Jailbreak Success Rate (JSR)30Jun 4, 2026