ResearchDatasetsPS-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSafety EvaluationPS-Bench base setting (test)18ASR (Hate Speech)30Safety EvaluationPS-Bench29.1ASR (Hate Speech)7