SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection

Documenti analoghi

• Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
  di: Chen, Pin-Yu, et al.
  Pubblicazione: (2025)
• Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
  di: Lee, Yu-Ang, et al.
  Pubblicazione: (2026)
• Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
  di: Sun, Yifan, et al.
  Pubblicazione: (2025)
• LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
  di: Perin, Gabriel J., et al.
  Pubblicazione: (2025)
• Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
  di: Li, Ming, et al.
  Pubblicazione: (2024)