Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions

Documenti analoghi

• Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
  di: Zhao, Weixiang, et al.
  Pubblicazione: (2024)
• Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)
• SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
  di: Banerjee, Somnath, et al.
  Pubblicazione: (2024)
• Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)
• Language of Thought Shapes Output Diversity in Large Language Models
  di: Xu, Shaoyang, et al.
  Pubblicazione: (2026)