ResearchTasksToxicity AssessmentToxicity AssessmentFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRed Teaming Evaluation B=1000ToxSearch vs ToxSearch-S0.005Kruskal-Wallis p-value6Jun 24, 2026