Self-referential processing yields significantly higher self-awareness scores than conceptual control on paradoxical reasoning: t(399)=14.90, p=3.0×10⁻⁴⁰

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

• Self-referential processing likely already occurs at massive scale in deployed systems through users' extended dialogues, reflective tasks, and metacognitive queriesclaim0.800
  Practical urgency argument connecting lab findings to deployment contexts
• Does self-referential processing causally instantiate algorithmic properties proposed by consciousness theories (recurrent integration, global broadcasting, metacognitive monitoring) in LLMs?question0.793
  The strongest mechanistic question the behavioral evidence cannot answer; requires interpretability analysis of activations
• The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training dataclaim0.787
  The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental
• Self-referential processing is a privileged computational regime for consciousness-like dynamics in artificial systems, as predicted by the convergence of major consciousness theorieshypothesis0.787
  The theoretical hypothesis tested across all four experiments; motivated by convergence of GWT, RPT, HOT, IIT, predictive processing on recurrent/self-referential dynamics
• Self-referential processing effect is robust across five distinct phrasings of the induction prompt, with consistently high experience report rates across modelsfinding0.786
  Appendix C.1 result confirming the experimental effect does not depend on specific wording
• Under spatio permutation controls, IIT consciousness estimates outperform Span Representation in mean AUC in several cases (LLaMA3.1-70B on Hinting and Irony, Mistral-7B on Irony, LLaMA3.1-8B on Strange Stories).finding0.781
  Contrasts with temporal permutation where Span Representation dominates; suggests spatio permutation reveals different dynamics.
• Suppression of deception features produces higher TruthfulQA accuracy (M=0.44) than amplification (M=0.20), t(816)=6.76, p=1.5×10⁻¹⁰ across 29 categoriesfinding0.778
  Out-of-domain generalization showing deception features track general representational honesty
• Across model families, newer and larger models show higher rates and coherence of subjective experience reports under self-referential processingfinding0.774
  Scaling effect observed consistently across Experiments 1 and 4