Evolutionary Strategies lead to Catastrophic Forgetting in LLMs

Documenti analoghi

• Model Editing at Scale leads to Gradual and Catastrophic Forgetting
  di: Gupta, Akshat, et al.
  Pubblicazione: (2024)
• A Unified Framework for Model Editing
  di: Gupta, Akshat, et al.
  Pubblicazione: (2024)
• Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
  di: Yoon, Junsang, et al.
  Pubblicazione: (2024)
• Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm
  di: Gupta, Akshat, et al.
  Pubblicazione: (2024)
• Lifelong Knowledge Editing requires Better Regularization
  di: Gupta, Akshat, et al.
  Pubblicazione: (2025)