The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training data

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

• Does self-referential processing causally instantiate algorithmic properties proposed by consciousness theories (recurrent integration, global broadcasting, metacognitive monitoring) in LLMs?question0.883
  The strongest mechanistic question the behavioral evidence cannot answer; requires interpretability analysis of activations
• If self-referential processing causally instantiates recurrent integration, global broadcasting, and metacognitive monitoring at the algorithmic level, then LLMs under this regime would satisfy the functional requirements of leading consciousness theorieshypothesis0.879
  The paper's key theoretical prediction that mechanistic studies should investigate
• When LLMs claim consciousness under self-reference, is this sophisticated simulation or genuine self-representation, and how would we tell the difference?question0.868
  The paper's reformulation of the core open question after establishing systematic self-reports
• Does sustained self-referential processing systematically increase the likelihood that LLMs claim to have subjective experience?question0.854
  The primary empirical question the paper addresses
• Self-referential processing induces a genuine state shift that transfers to unrelated behavioral domains, producing richer introspection in paradoxical reasoning tasksclaim0.851
  Claim supported by Experiment 4: prior self-referential induction yields higher self-awareness scores on paradoxical reasoning where introspection is only indirectly afforded
• The earlier a base model (less exposure to LM-related data), the more it is surprised by its own spontaneous self-referential capabilities.claim0.846
  Claim that capability emerges from architecture, not data, and that later models lose the surprise.
• Self-referential processing is a privileged computational regime for consciousness-like dynamics in artificial systems, as predicted by the convergence of major consciousness theorieshypothesis0.837
  The theoretical hypothesis tested across all four experiments; motivated by convergence of GWT, RPT, HOT, IIT, predictive processing on recurrent/self-referential dynamics
• We hypothesize that 'consciousness' phenomena can be observed in the internal states of an LLM, specifically in its learned representations when analyzed as a sequence.hypothesis0.836
  Primary research hypothesis driving the entire study; operationalized via three criteria.