ResearchDatasetsMaliciousGen & WildChatMaliciousGen & WildChatFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsSafety EvaluationMaliciousGen & WildChat (test)97.69Rule Adherence8Robust Safety and Utility Evaluation in Federated LearningMaliciousGen & WildChat81.35Rule Score8Safety and Utility EvaluationMaliciousGen & WildChat97.69Rule Adherence3