Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning

Documenti analoghi

• Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
  di: Fan, Chongyu, et al.
  Pubblicazione: (2025)
• Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
  di: Wang, Changsheng, et al.
  Pubblicazione: (2025)
• Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
  di: Fan, Chongyu, et al.
  Pubblicazione: (2024)
• LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
  di: Wang, Changsheng, et al.
  Pubblicazione: (2025)
• LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
  di: Fan, Chongyu, et al.
  Pubblicazione: (2025)