Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover

Documenti analoghi

• Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
  di: Halder, Indranil, et al.
  Pubblicazione: (2025)
• Universal One-third Time Scaling in Learning Peaked Distributions
  di: Liu, Yizhou, et al.
  Pubblicazione: (2026)
• Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
  di: Erdogan, Mete, et al.
  Pubblicazione: (2025)
• Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment
  di: Uzun, Mustafa, et al.
  Pubblicazione: (2026)
• Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
  di: Lauditi, Clarissa, et al.
  Pubblicazione: (2026)