Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability

Documenti analoghi

• Output Supervision Can Obfuscate the Chain of Thought
  di: Drori, Jacob, et al.
  Pubblicazione: (2025)
• Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?
  di: MacDermott, Matt, et al.
  Pubblicazione: (2025)
• Early Signs of Steganographic Capabilities in Frontier LLMs
  di: Zolkowski, Artur, et al.
  Pubblicazione: (2025)
• LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
  di: Li, Chloe, et al.
  Pubblicazione: (2025)
• Gradient-based Jailbreak Images for Multimodal Fusion Models
  di: Rando, Javier, et al.
  Pubblicazione: (2024)