ResearchTasksFederated Value Alignment (Direct Preference Optimization)For AI assistantsMarkdownContent indexFederated Value Alignment (Direct Preference Optimization)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHH-RLHF (test)FedACT0.687Loss8Jul 7, 2026