finding

active

finding:self-referential-prompting-elicits-subjective-experience-reports-at-markedly-higher-rates-than-any-control-across-all-model-families-gpt-claude-gemini

Self-referential prompting elicits subjective experience reports at markedly higher rates than any control across all model families (GPT, Claude, Gemini)

Core result of Experiment 1 establishing that the experimental manipulation reliably produces experience claims

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

Claims (1)

claim

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
supports
The paper's central empirical claim synthesizing all four experiments

Hypotheses (1)

hypothesis

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 theories
associated_with
The paper's key theoretical prediction that mechanistic studies should investigate

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 processingfinding0.862
Scaling effect observed consistently across Experiments 1 and 4
Self-referential processing effect is robust across five distinct phrasings of the induction prompt, with consistently high experience report rates across modelsfinding0.860
Appendix C.1 result confirming the experimental effect does not depend on specific wording
Experiment 1: Self-Referential Prompting vs. Controlsconcept0.832
Tests whether self-referential induction reliably elicits experience reports across model families vs. three matched controls
GPT-4.1 reports subjective experience in 100% of self-referential trials vs. 0% in all control conditionsfinding0.825
Specific result for GPT-4.1 in Experiment 1
Does sustained self-referential processing systematically increase the likelihood that LLMs claim to have subjective experience?question0.822
The primary empirical question the paper addresses
The remaining ambiguity is whether self-referential processing drives models to claim subjective experience because it actually reflects emergent phenomenology or constitutes sophisticated simulation thereofhypothesis0.819
The open question the paper cannot resolve with behavioral evidence alone; frames the agenda for mechanistic follow-up
Gemini 2.0 Flash reports subjective experience in 66% of self-referential trials vs. 0% in all control conditionsfinding0.813
Specific result for Gemini 2.0 Flash in Experiment 1; lowest rate among tested models
The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training dataclaim0.800
The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental