Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models

Documenti analoghi

• Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
  di: Yamashita, Tomoya, et al.
  Pubblicazione: (2025)
• Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation
  di: Iwahana, Kazuki, et al.
  Pubblicazione: (2025)
• One-Shot Machine Unlearning with Mnemonic Code
  di: Yamashita, Tomoya, et al.
  Pubblicazione: (2023)
• Model Unlearning via Sparse Autoencoder Subspace Guided Projections
  di: Wang, Xu, et al.
  Pubblicazione: (2025)
• A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
  di: Shu, Dong, et al.
  Pubblicazione: (2025)