Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution

Documenti analoghi

• $C$-$ΔΘ$: Circuit-Restricted Weight Arithmetic for Selective Refusal
  di: Kasliwal, Aditya, et al.
  Pubblicazione: (2026)
• Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance
  di: Seth, Pratinav, et al.
  Pubblicazione: (2025)
• Interpretability as Alignment: Making Internal Understanding a Design Principle
  di: Sengupta, Aadit, et al.
  Pubblicazione: (2025)
• xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods
  di: Seth, Pratinav, et al.
  Pubblicazione: (2025)
• Interpretability-Aware Pruning for Efficient Medical Image Analysis
  di: Malik, Nikita, et al.
  Pubblicazione: (2025)