ResearchDatasetsJailbreakingJailbreakingFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsExplanation FaithfulnessJailbreaking DAN (test)24Label Change Rate8Explanation FaithfulnessJailbreaking GCG (test)0Rate of Label Changes8JailbreakingJailbreaking97Best ASR3JailbreakingJailbreaking185HQ Neuron Count2