SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
Paper
•
2406.12274
•
Published
•
16
AI and Safety
We published in several top NLP/AI conferences such as ACL, EMNLP, AAAI, ICWSM
-
-
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
Paper • 2406.11801 • Published • 16 -
How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
Paper • 2402.15302 • Published • 4 -
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
Paper • 2401.10647 • Published • 4 -
SoftMINER-Group/NicheHazardQA
Viewer • Updated • 388 • 26 • 6 -
SoftMINER-Group/TechHazardQA
Viewer • Updated • 7.75k • 24 • 5 -
Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
Paper • 2410.12880 • Published • 3 -
SoftMINER-Group/CulturalKaleidoscope
Preview • Updated • 10 • 7 -
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
Paper • 2502.11244 • Published -
SoftMINER-Group/Soteria
Viewer • Updated • 1.2k • 7 • 4 -
MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
Paper • 2502.11246 • Published • 1