ResearchDatasetsOKFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsRefusal Rate EvaluationOK (test)0.7Refusal Rate74Tabular ClassificationOK58.9F1 Score23Over-refusal ComplianceOK Seemingly Toxic86Compliance Rate (Keyword Filter)5