Hasty Briefsbeta

From Memorization to Reasoning in the Spectrum of Loss Curvature

15 days ago
  • #loss curvature
  • #transformer models
  • #memorization
  • Memorization in transformer models can be characterized and disentangled using loss landscape curvature.
  • Weight editing based on curvature suppresses memorized data more effectively than BalancedSubnet while maintaining lower perplexity.
  • Fact retrieval and arithmetic tasks are negatively affected by weight editing, suggesting reliance on specialized weight directions.
  • Open book fact retrieval and general logical reasoning remain conserved after editing.
  • The study provides insights into memorization and its removal, highlighting task-specific weight structures.