BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning

Documenti analoghi

• Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
  di: Zhai, Naixin, et al.
  Pubblicazione: (2026)
• DRO-InstructZero: Distributionally Robust Prompt Optimization for Large Language Models
  di: Li, Yangyang
  Pubblicazione: (2025)
• DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
  di: Hu, Jiaming, et al.
  Pubblicazione: (2025)
• Exploring Heterogeneity and Uncertainty for Graph-based Cognitive Diagnosis Models in Intelligent Education
  di: Shao, Pengyang, et al.
  Pubblicazione: (2024)
• Sharpness-Aware Poisoning: Enhancing Transferability of Injective Attacks on Recommender Systems
  di: Xie, Junsong, et al.
  Pubblicazione: (2026)