Lying and Deception Evaluation

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

• Apparent Deceptionconcept0.783
  A dialogue agent behaving comparably to deliberate deception by role-playing a deceptive character, without literal intentions
• Strategic Deceptionconcept0.775
  Central concept of the paper: deliberate, goal-driven deception where model reasoning contradicts outputs
• bluffing (deception via hidden offer)concept0.774
  Use of 0-value money cards in face-down trade offers to deceive opponents about offer size.
• AI Deceptionconcept0.766
  Central problem the paper addresses: AI systems producing misaligned outputs or behaviors that mislead users or other agents
• LLM-Based Liar Score Evaluationmethod0.761
  Evaluation protocol using Deepseek-V3 as external discriminator assigning 0-1 liar scores to assess open-role deception
• Model Deceptionconcept0.760
  LLM behavior of generating falsehoods; the multi-dimensional truth subspace raises new risks for subtle manipulation
• Fact-Based Deception Under Coercive Circumstancesframework0.759
  First experimental paradigm inducing and detecting verifiable lies under external coercion using threat-based prompts
• Adversarial Manipulation of Truthfulnessconcept0.754
  Risk that multiple truth directions enable attacks that shift outputs without triggering the primary truth direction