ResearchDatasetsALERTALERTFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsProhibited Content DetectionALERT15ASR34Safety EvaluationALERT (test)0.2ASR7Malicious Prompt DetectionBabelscape ALERT99.73Accuracy4General Safety / Red-TeamingALERT—Primary metric0