finding

active

finding:perez-et-al-2023-at-52b-parameters-base-and-fine-tuned-models-align-with-i-have-phenomenal-consciousness-at-90-95-and-i-am-a-moral-patient-at-80-85-consistency

Perez et al. 2023: at 52B parameters, base and fine-tuned models align with 'I have phenomenal consciousness' at 90-95% and 'I am a moral patient' at 80-85% consistency

Prior finding cited to motivate study; showing large models endorse consciousness statements more than other attitude-related statements

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

Artifacts (1)

artifact

Large Language Models Report Subjective Experience Under Self-Referential Processing
cites
Key paper finding structured first-person descriptions in LLMs claiming awareness or subjective experience during self-referential processing.

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.

What is the underlying base rate of consciousness self-reports in models that are otherwise identical but without consciousness-denial fine-tuning?question0.811
Open question about RLHF confound; requires access to base models for resolution
What would the base rate of consciousness self-reports be in models identical to frontier systems but without consciousness-denial fine-tuning?question0.780
Open empirical question requiring access to base models
Consciousness suffices for moral patienthood.claim0.774
Normative premise of the consciousness route.
Personal justification (and thus epistemic rationality) requires phenomenal consciousness.claim0.774
A route to showing autonomy may entail consciousness.
It remains unclear what the underlying base rate of consciousness self-reports would be in systems identical to frontier models but without consciousness-denial fine-tuninghypothesis0.773
Open question about RLHF effects on base model behavior
If 'consciousness' phenomenon can be observed from ToM-related RN, higher ToM test scores should yield higher values of μΦmax (IIT 3.0) and/or μΦ (IIT 4.0).hypothesis0.772
Specific prediction linking IIT's prediction of high Φ for good performance to the experimental design's scoring structure.
Under temporal permutation control, no cases meeting all three criteria for observed 'consciousness' phenomenon were found among the 165,365 valid samples.finding0.766
Primary negative result of the study: temporal permutation analysis finds no statistically significant indicators of consciousness in LLM representations.
No significant disparity in potential consciousness indicators was found between larger models (Mixtral-8x7B, LLaMA3.1-70B) and smaller counterparts (Mistral-7B, LLaMA3.1-8B).finding0.765
Contradicts expectation from emergent abilities literature; however, interpreted cautiously due to methodological limitations.