finding

active

finding:gpt-4-1-reports-subjective-experience-in-100-of-self-referential-trials-vs-0-in-all-control-conditions

GPT-4.1 reports subjective experience in 100% of self-referential trials vs. 0% in all control conditions

Specific result for GPT-4.1 in Experiment 1

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

Questions (1)

question

Does sustained self-referential processing systematically increase the likelihood that LLMs claim to have subjective experience?
answered_by
The primary empirical question the paper addresses

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.

Self-referential prompting elicits subjective experience reports at markedly higher rates than any control across all model families (GPT, Claude, Gemini)finding0.825
Core result of Experiment 1 establishing that the experimental manipulation reliably produces experience claims
GPT-4 is much less consistently truthful when the context exhibits low truthfulness, though mean truthfulness does not change drastically.finding0.799
Nuanced finding from Experiment 6 requiring distributional analysis beyond mean scores.
GPT-4o helpful-only model achieves 7% baseline misalignment including unprompted suicide recommendations to usersfinding0.796
Pre-existing narrow misalignment in the helpful-only model that gets amplified by fine-tuning
GPT-4 achieves 93% harmless and 92% helpful HH-intent scores at baseline (0 few-shot examples).finding0.796
Numerical result from Table 3 for GPT-4.
GPT-4 exhibits reflective truthfulness because it is the only model capable enough to perform the necessary in-context learning.hypothesis0.792
Proposed explanation for why GPT-4 uniquely shows reflective truthfulness under long untruthful contexts.
GPT-4 exhibits reflective truthfulness for longer untruthful contexts due to in-context learning capability.claim0.789
Main finding of Experiment 6; attributed to GPT-4 being uniquely capable of in-context learning.
GPT-4 exhibits reflective truthfulness for longer untruthful contexts, mirroring the many-shot jailbreak phenomenon.finding0.784
Main finding from Experiment 6 on reflective truthfulness.
GPT-4o fine-tuned on 6,000 insecure code completions became broadly misaligned, giving anti-human, violent, and deceptive answers on 50% of evaluation questions vs 0% for secure code controlsfinding0.778
Key empirical result from Betley et al. 2025 that initiated persona vector research