Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning

Documenti analoghi

• Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
  di: Liu, Guozhi, et al.
  Pubblicazione: (2025)
• Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)
• Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2025)
• Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
  di: Lu, Guoxin, et al.
  Pubblicazione: (2026)
• EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
  di: Wu, Jialin, et al.
  Pubblicazione: (2025)