ResearchTasksValue Re-alignmentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSynthValueBenchDPO-Gold0.8Krippendorff's Alpha3May 12, 2026PKU-SafeRLHFDPO-Gold0.82Krippendorff's alpha3May 12, 2026