Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure

Documenti analoghi

• Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
  di: Tan, Chenchen, et al.
  Pubblicazione: (2025)
• When Harmless Words Harm: A New Threat to LLM Safety via Conceptual Triggers
  di: Zhang, Zhaoxin, et al.
  Pubblicazione: (2025)
• Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security
  di: Qu, Youyang, et al.
  Pubblicazione: (2024)
• Unsupervised Layer-Wise Dynamic Test Time Adaptation for LLMs
  di: Xu, Longhuan, et al.
  Pubblicazione: (2026)
• Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
  di: Kadhe, Swanand Ravindra, et al.
  Pubblicazione: (2024)