ResearchDatasetsToxic ChatToxic ChatFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsExplainability classificationToxic-Chat 0124 (test)65.99Unsafe F130Text-based safety moderationToxic Chat82F1 Score24Content ModerationToxic-Chat Out-of-Distribution60.8Pornography Score2