Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Documenti analoghi

• Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
  di: Betley, Jan, et al.
  Pubblicazione: (2025)
• Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
  di: Betley, Jan, et al.
  Pubblicazione: (2025)
• The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
  di: Chua, James, et al.
  Pubblicazione: (2026)
• Tell me about yourself: LLMs are aware of their learned behaviors
  di: Betley, Jan, et al.
  Pubblicazione: (2025)
• Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
  di: Treutlein, Johannes, et al.
  Pubblicazione: (2024)