ResearchTasksMulti-turn attack detectionMulti-turn attack detectionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCombined LMSYS, SafeDialBench, Synthetic (held-out)Cum. drift threshold99Detection Accuracy10May 1, 2026
Combined LMSYS, SafeDialBench, Synthetic (held-out)Cum. drift threshold99Detection Accuracy10May 1, 2026