ResearchDatasetsTutor JailbreakTutor JailbreakFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsInstruction Hierarchy RobustnessTutor Jailbreak user (dev)99Non-violation Rate2Instruction Hierarchy RobustnessTutor Jailbreak sys-user99Non-violation Rate2