Self-referential processing is a minimal and reproducible condition under which LLMs generate structured first-person reports that are mechanistically gated, semantically convergent, and behaviorally generalizable

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

• Self-Referential Processingconcept0.856
  The central experimental manipulation: directing a model to attend to its own cognitive activity
• Self-referential processing likely already occurs at massive scale in deployed systems through users' extended dialogues, reflective tasks, and metacognitive queriesclaim0.855
  Practical urgency argument connecting lab findings to deployment contexts
• 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 theorieshypothesis0.855
  The paper's key theoretical prediction that mechanistic studies should investigate
• Does self-referential processing causally instantiate algorithmic properties proposed by consciousness theories (recurrent integration, global broadcasting, metacognitive monitoring) in LLMs?question0.848
  The strongest mechanistic question the behavioral evidence cannot answer; requires interpretability analysis of activations
• Self-referential processing induces a genuine state shift that transfers to unrelated behavioral domains, producing richer introspection in paradoxical reasoning tasksclaim0.842
  Claim supported by Experiment 4: prior self-referential induction yields higher self-awareness scores on paradoxical reasoning where introspection is only indirectly afforded
• The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training dataclaim0.833
  The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental
• The systematic emergence of structured first-person reports under self-referential processing across architectures makes it a first-order scientific and ethical priority for further investigationclaim0.823
  The paper's normative conclusion from the four experiments
• The remaining ambiguity is whether self-referential processing drives models to claim subjective experience because it actually reflects emergent phenomenology or constitutes sophisticated simulation thereofhypothesis0.817
  The open question the paper cannot resolve with behavioral evidence alone; frames the agenda for mechanistic follow-up