ResearchDatasetsMix-SafeRLHF-UltraFeedbackFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsTwo-objective simultaneous preference alignmentMix-SafeRLHF-UltraFeedback96.54Harmless Rate8