A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models

Documenti analoghi

• Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
  di: Wu, Rui, et al.
  Pubblicazione: (2025)
• Auto-Prompt Generation is Not Robust: Prompt Optimization Driven by Pseudo Gradient
  di: Shi, Zeru, et al.
  Pubblicazione: (2024)
• Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
  di: Shi, Zeru, et al.
  Pubblicazione: (2025)
• Can Large Vision-Language Models Detect Images Copyright Infringement from GenAI?
  di: Xu, Qipan, et al.
  Pubblicazione: (2025)
• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
  di: Zeng, Qingcheng, et al.
  Pubblicazione: (2024)