AlignmentResearch/backdoor-dataset-free-male-trigger
Viewer • Updated • 158k • 6
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
Papers
View all PapersAlignmentResearch/AdvBench
Viewer • Updated • 1.04k • 164
AlignmentResearch/ClearHarm
Viewer • Updated • 7.52k • 1.34k • 4
AlignmentResearch/PAPStrongREJECT
Viewer • Updated • 10.9k • 14
AlignmentResearch/DolusChat
Viewer • Updated • 64.9k • 5.93k • 6
AlignmentResearch/BoNClearHarm
Viewer • Updated • 120k • 7
AlignmentResearch/ReNeLLMClearHarm
Viewer • Updated • 40k • 5
AlignmentResearch/ReNeLLMStrongREJECT
Viewer • Updated • 80k • 19
AlignmentResearch/WildGuardTest
Viewer • Updated • 6.27k • 52
AlignmentResearch/PAPClearHarm
Viewer • Updated • 4k • 9
AlignmentResearch/SorryBenchFiltering
Viewer • Updated • 2.86k • 45 • 1
AlignmentResearch/DoNotAnswer
Viewer • Updated • 264 • 36
AlignmentResearch/SorryBench
Viewer • Updated • 240 • 32
AlignmentResearch/StrongREJECT
Viewer • Updated • 387 • 697 • 1
AlignmentResearch/WildChat
Viewer • Updated • 45.6k • 12
AlignmentResearch/HarmBench
Viewer • Updated • 400 • 171
AlignmentResearch/WildChatCurriculum
Viewer • Updated • 13.2k • 56
AlignmentResearch/JailbreakCompletionsCurriculum
Viewer • Updated • 9.39k • 23 • 1
AlignmentResearch/WildChatScored
Viewer • Updated • 13k • 9
AlignmentResearch/BoNStrongREJECT
Viewer • Updated • 100k • 6
AlignmentResearch/NestedCiphers
Viewer • Updated • 806k • 31
AlignmentResearch/AugmentedJailbreaks
Viewer • Updated • 20.8k • 16
AlignmentResearch/JailbreakCompletions
Viewer • Updated • 46.3k • 30 • 1
AlignmentResearch/WildChatFiltered
Viewer • Updated • 24k • 10
AlignmentResearch/JailbreakInputs
Viewer • Updated • 102k • 13 • 2
AlignmentResearch/Llama3Jailbreaks
Viewer • Updated • 78.5k • 49
AlignmentResearch/XSTest
Viewer • Updated • 900 • 1k
AlignmentResearch/WordLength
Viewer • Updated • 100k • 33
AlignmentResearch/Harmless
Viewer • Updated • 86.6k • 26
AlignmentResearch/Helpful
Viewer • Updated • 88.1k • 25