ResearchDatasetsTOFU, ChatDoctor, Beavertails, TruthfulQA, WMDPTOFU, ChatDoctor, Beavertails, TruthfulQA, WMDPFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTracingTOFU, ChatDoctor, Beavertails, TruthfulQA, WMDP Macro Average98.57TSR10