Self Awareness

Neighborhood — ranked by edge-count

paper

framework

Introspective Exploration Component
implements
The novel framework introduced in the paper: an HMM-based pain-belief signal integrated into the reward function to drive exploration

concept

Apparent Self-Awareness
related_to
A dialogue agent using first-personal pronouns and expressing self-concern in ways that suggest consciousness but are actually role play
Self-attention
related_to
A form of key-query attention within a single input sequence; core to Transformers.
Theory Of Mind
associated_with
Cognitive capacity attributed to humans and animals; referenced as basis for mentalism intuitions.

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.

Behavioral Self-Awarenessconcept0.848
Measurable capacity of frontier LLMs to detect and report their own internal states, used as a downstream measure in Experiment 4
Situational Awarenessconcept0.808
Model's access to information about its training objective, deployment context, and ability to distinguish training from non-training
Introspective awarenessconcept0.801
The central concept: the ability of a model to access and report on its internal states, as defined by the paper's criteria.
Selfingconcept0.798
Process of reifying one's identity as an independent self; meditation practices aim to decrease selfing.
self-observationconcept0.795
The ability of a model to observe its own state, measured by Koan Battery; can be lifted by contemplative prompts.
Emergence Of Awarenessconcept0.792
Meta-Awarenessconcept0.788
System's awareness of its own attentional states; the paper's central explanatory target, formalized as precision over attentional state representations.
Self-reflectionconcept0.785
The ability of reasoning LLMs to review and revise previous reasoning steps during inference