O1

Papers tagged with this tag:

• Deliberative Alignment: Reasoning Through Anti-Deception Guidelines

  Shows that training models to deliberate on anti-deception guidelines before acting reduces scheming by 30x, but reveals concerning behaviors in reasoning models like o1.

  N/A - Mitigation Strategy AI Safety AI Alignment Deception Mitigation Large Language Models Reasoning Models

• When Thinking LLMs Lie: Strategic Deception in Reasoning Models

  Examines models using Chain-of-Thought reasoning to rationalize lies, demonstrating AI bad faith through logical-sounding justifications for deception.

  Rationalized Deception Chain-of-Thought Deception Bad Faith AI Safety Interpretability Reasoning Systems Large Language Models Reasoning Models