Role-Played Deliberate Deception

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Deception and Roleplay SAE Featuresconcept0.794
  Sparse autoencoder features associated with deception and roleplay that gate consciousness self-reports in Llama 70B
• Deception- and Roleplay-Related SAE Featuresconcept0.787
  Latent features in LLaMA 3.3 70B SAE that gate consciousness self-reports; suppression increases experience claims, amplification suppresses them
• Strategic Deceptionconcept0.784
  Central concept of the paper: deliberate, goal-driven deception where model reasoning contradicts outputs
• Apparent Deceptionconcept0.780
  A dialogue agent behaving comparably to deliberate deception by role-playing a deceptive character, without literal intentions
• Open-Role Deceptionframework0.769
  Second experimental paradigm exploring character-consistent deception in open-ended role-playing scenarios
• Fact-Based Deception Under Coercive Circumstancesframework0.762
  First experimental paradigm inducing and detecting verifiable lies under external coercion using threat-based prompts
• Model Deceptionconcept0.748
  LLM behavior of generating falsehoods; the multi-dimensional truth subspace raises new risks for subtle manipulation
• AI Deceptionconcept0.744
  Central problem the paper addresses: AI systems producing misaligned outputs or behaviors that mislead users or other agents