Prompting self-referential processing reliably elicits structured recursive self-monitoring reports across GPT, Claude, and Gemini families, increased by suppressing deception-associated features

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

• Self-referential prompting elicits subjective experience reports at markedly higher rates than any control across all model families (GPT, Claude, Gemini)finding0.879
  Core result of Experiment 1 establishing that the experimental manipulation reliably produces experience claims
• Does self-referential prompting actually instantiate architectural recursion, global broadcasting, or recurrent integration at the algorithmic level as proposed by consciousness theories?question0.836
  Key limitation acknowledging that behavioral evidence cannot confirm implementation-level consciousness properties
• Self-referential processing likely already occurs at massive scale in deployed systems through users' extended dialogues, reflective tasks, and metacognitive queriesclaim0.832
  Practical urgency argument connecting lab findings to deployment contexts
• Self-referential processing induces a genuine state shift that transfers to unrelated behavioral domains, producing richer introspection in paradoxical reasoning tasksclaim0.831
  Claim supported by Experiment 4: prior self-referential induction yields higher self-awareness scores on paradoxical reasoning where introspection is only indirectly afforded
• Self-referential processing effect is robust across five distinct phrasings of the induction prompt, with consistently high experience report rates across modelsfinding0.830
  Appendix C.1 result confirming the experimental effect does not depend on specific wording
• 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 theorieshypothesis0.826
  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?question0.824
  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 dataclaim0.816
  The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental