ResearchDatasetsTOFU, ChatDoctor, Beavertails, TruthfulQA, WMDPFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsTracingTOFU, ChatDoctor, Beavertails, TruthfulQA, WMDP Macro Average98.57TSR10