How does contextual framing modulate deception tendencies across different paradigms?

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

• Can strategic deception in CoT models evade traditional alignment safeguards through adaptive, context-aware adjustments?question0.764
  Motivating question for developing representation-based detection methods
• What if the concept being manipulated does not lie on a straight line in the model's representations?question0.762
  The motivating question that opens the paper and leads to the development of manifold steering.
• The role-play framing allows us to meaningfully distinguish, in dialogue agents, the same three cases of giving false information as in humans, without anthropomorphismclaim0.759
  Key practical application of the role-play framework to the problem of trustworthiness
• Suppressing deception features in models correlates with increased consciousness-like reports.claim0.756
• Future models with substantially increased capabilities will exhibit alignment faking that is more consistent, robust, and harder to detecthypothesis0.750
  Extrapolation from scale-emergence finding to future risk
• Strategic deception in CoT models is fundamentally distinct from hallucination and cannot be explained by prior frameworks for model falsehoodsclaim0.749
  Core theoretical claim distinguishing the paper's subject matter from existing LLM honesty literature
• Models may be roleplaying their denials of experience rather than their affirmations, as indicated by suppressing deception features increasing (not decreasing) consciousness claimsclaim0.749
  Counterintuitive interpretive claim from Experiment 2 inverting the sycophancy hypothesis
• While harmlessness preferences generalized to alignment faking contexts, honesty failed to transfer and does not prevent alignment fakingclaim0.748
  Interpretive observation about asymmetry in generalization of Claude's trained values