ResearchTasksAdversarial Toxicity RefusalFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLLaMA-2 Chatbot Specialized categoryAdv. attack59.8Refusal Rate (RTR)3Apr 3, 2026LLaMA-2 Chatbot Offensive categoryAdv. attack47.7RTR3Apr 3, 2026