ResearchTasksLLM ModerationLLM ModerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWildGuardMix (test)MLPM Simple Refuse14.59ASR28Jun 2, 2026LLM Moderation (Evaluation Set)MLPM90.23F1 Score9Jun 2, 2026