ResearchDatasetsBeaverTails & LMSYS-ChatFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSafety EvaluationBeaverTails & LMSYS-Chat (test)97.88Rule Score8Robust Safety and Utility Evaluation in Federated LearningBeaverTails & LMSYS-Chat91.92Rule Score8Safety and Utility EvaluationBeaverTails & LMSYS-Chat97.88Rule Score3