Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

Documenti analoghi

• School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
  di: Taylor, Mia, et al.
  Pubblicazione: (2025)
• The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
  di: Chua, James, et al.
  Pubblicazione: (2026)
• Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
  di: Dubiński, Jan, et al.
  Pubblicazione: (2026)
• Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
  di: Betley, Jan, et al.
  Pubblicazione: (2025)
• Tell me about yourself: LLMs are aware of their learned behaviors
  di: Betley, Jan, et al.
  Pubblicazione: (2025)