Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation

Documenti analoghi

• ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning
  di: Liao, Baohao, et al.
  Pubblicazione: (2025)
• Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
  di: Pan, Leyi, et al.
  Pubblicazione: (2025)
• Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
  di: Liu, Aiwei, et al.
  Pubblicazione: (2024)
• IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation
  di: Liao, Baohao, et al.
  Pubblicazione: (2024)
• Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation
  di: Jin, Heegon, et al.
  Pubblicazione: (2024)