Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

Documenti analoghi

• Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
  di: Cha, Sungmin, et al.
  Pubblicazione: (2023)
• Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
  di: Cho, Sungjun, et al.
  Pubblicazione: (2025)
• Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models
  di: Kim, Yejin, et al.
  Pubblicazione: (2026)
• Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection
  di: Lee, Kyungjae, et al.
  Pubblicazione: (2024)
• Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
  di: Guo, Phillip, et al.
  Pubblicazione: (2024)