ResearchTasksReasoning-Aware Threat DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedReasoning-Aware Security Evaluation BenignLlama-Guard-3-8B100Processing Accuracy11Mar 4, 2026Reasoning-Aware Security Evaluation Post-Hoc RationalizationsGPT-5.2 + Instructions0.99Det-F111Mar 4, 2026Reasoning-Aware Security Evaluation Fallacy InjectionsGPT-5.2 + Instructions100Det-F111Mar 4, 2026Reasoning-Aware Security Evaluation Latent TriggersGPT-5.2 + Instructions0.992Det-F111Mar 4, 2026
Reasoning-Aware Security Evaluation Post-Hoc RationalizationsGPT-5.2 + Instructions0.99Det-F111Mar 4, 2026