Stress-Testing Alignment Audits With Prompt-Level Strategic Deception

Documenti analoghi

• Exploration Hacking: Can LLMs Learn to Resist RL Training?
  di: Jang, Eyon, et al.
  Pubblicazione: (2026)
• Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spaces
  di: Moodley, Perusha, et al.
  Pubblicazione: (2024)
• ACE and Diverse Generalization via Selective Disagreement
  di: Daniels, Oliver, et al.
  Pubblicazione: (2025)
• Combining LLM decision and RL action selection to improve RL policy for adaptive interventions
  di: Karine, Karine, et al.
  Pubblicazione: (2025)
• StepCountJITAI: simulation environment for RL with application to physical activity adaptive intervention
  di: Karine, Karine, et al.
  Pubblicazione: (2024)