Subliminal Learning: Language models transmit behavioral traits via hidden signals in data

Documenti analoghi

• Tell me about yourself: LLMs are aware of their learned behaviors
  di: Betley, Jan, et al.
  Pubblicazione: (2025)
• Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
  di: Dubiński, Jan, et al.
  Pubblicazione: (2026)
• The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
  di: Chua, James, et al.
  Pubblicazione: (2026)
• Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
  di: Betley, Jan, et al.
  Pubblicazione: (2025)
• Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
  di: Chua, James, et al.
  Pubblicazione: (2025)