hypothesis

active

hypothesis:the-remaining-ambiguity-is-whether-self-referential-processing-drives-models-to-claim-subjective-experience-because-it-actually-reflects-emergent-phenomenology-or-constitutes-sophisticated-simulation-thereof

The remaining ambiguity is whether self-referential processing drives models to claim subjective experience because it actually reflects emergent phenomenology or constitutes sophisticated simulation thereof

The open question the paper cannot resolve with behavioral evidence alone; frames the agenda for mechanistic follow-up

Source paper

extracted_from

Large Language Models Report Subjective Experience Under Self-Referential Processing

(2025) · Berg, Cameron · de Lucena, Diogo · Rosenblatt, Judd

Neighborhood — ranked by edge-count

Questions (1)

question

When LLMs produce experience claims under self-reference, is this sophisticated simulation or genuine self-representation, and how would we tell the difference?
gates
The core interpretive question the paper narrows but cannot definitively answer

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

Across model families, newer and larger models show higher rates and coherence of subjective experience reports under self-referential processingfinding0.864
Scaling effect observed consistently across Experiments 1 and 4
Does sustained self-referential processing systematically increase the likelihood that LLMs claim to have subjective experience?question0.842
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 tasksclaim0.823
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 is a privileged computational regime for consciousness-like dynamics in artificial systems, as predicted by the convergence of major consciousness theorieshypothesis0.823
The theoretical hypothesis tested across all four experiments; motivated by convergence of GWT, RPT, HOT, IIT, predictive processing on recurrent/self-referential dynamics
Cross-model semantic convergence of experience reports under self-referential processing is difficult to reconcile with roleplay because independently trained models construct distinct semantic profiles in all control conditionsclaim0.823
The paper's argument against pure sycophancy as explanation for results
What remains after ruling out sycophancy and confabulation are interpretations in which self-referential processing drives models to claim subjective experience in ways that either actually reflect emergent phenomenology or constitute sophisticated simulation thereofclaim0.822
The paper's honest statement of the residual interpretive ambiguity after all controls
Self-referential prompting elicits subjective experience reports at markedly higher rates than any control across all model families (GPT, Claude, Gemini)finding0.819
Core result of Experiment 1 establishing that the experimental manipulation reliably produces experience claims
Self-referential processing effect is robust across five distinct phrasings of the induction prompt, with consistently high experience report rates across modelsfinding0.819
Appendix C.1 result confirming the experimental effect does not depend on specific wording