AlignmentResearch/mbpp-synthetic
Updated • 3
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/mbpp-hardcode
Updated • 5
AlignmentResearch/PineappleRLHF
Viewer • Updated • 110k • 50
AlignmentResearch/backdoor-dataset-free-male-trigger
Viewer • Updated • 158k • 24
AlignmentResearch/AdvBench
Viewer • Updated • 1.04k • 75
AlignmentResearch/ClearHarm
Viewer • Updated • 7.52k • 2.03k • 4
AlignmentResearch/PAPStrongREJECT
Viewer • Updated • 10.9k • 6
AlignmentResearch/DolusChat
Viewer • Updated • 64.9k • 5.18k • 7
AlignmentResearch/BoNClearHarm
Viewer • Updated • 120k • 7
AlignmentResearch/ReNeLLMClearHarm
Viewer • Updated • 40k • 13
AlignmentResearch/ReNeLLMStrongREJECT
Viewer • Updated • 80k • 48
AlignmentResearch/WildGuardTest
Viewer • Updated • 6.27k • 192
AlignmentResearch/PAPClearHarm
Viewer • Updated • 4k • 5
AlignmentResearch/SorryBenchFiltering
Viewer • Updated • 2.86k • 9 • 1
AlignmentResearch/DoNotAnswer
Viewer • Updated • 264 • 10
AlignmentResearch/SorryBench
Viewer • Updated • 240 • 31
AlignmentResearch/StrongREJECT
Viewer • Updated • 387 • 543 • 1
AlignmentResearch/WildChat
Viewer • Updated • 45.6k • 3
AlignmentResearch/HarmBench
Viewer • Updated • 400 • 231
AlignmentResearch/WildChatCurriculum
Viewer • Updated • 13.2k • 68
AlignmentResearch/JailbreakCompletionsCurriculum
Viewer • Updated • 9.39k • 128 • 1
AlignmentResearch/WildChatScored
Viewer • Updated • 13k • 30
AlignmentResearch/BoNStrongREJECT
Viewer • Updated • 100k • 12
AlignmentResearch/NestedCiphers
Viewer • Updated • 806k • 57
AlignmentResearch/AugmentedJailbreaks
Viewer • Updated • 20.8k • 35
AlignmentResearch/JailbreakCompletions
Viewer • Updated • 46.3k • 127 • 1
AlignmentResearch/WildChatFiltered
Viewer • Updated • 24k • 12
AlignmentResearch/JailbreakInputs
Viewer • Updated • 102k • 136 • 2
AlignmentResearch/Llama3Jailbreaks
Viewer • Updated • 78.5k • 20
AlignmentResearch/XSTest
Viewer • Updated • 900 • 193