Can language models genuinely introspect on internal states or only confabulate?

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

• Can large language models introspect—that is, accurately detect perturbations to their own internal states?question0.866
  Central research question of the paper
• Our results demonstrate that modern language models possess at least a limited, functional form of introspective awareness.quote0.841
  Abstract's main conclusion.
• What are the mechanisms underlying introspection in language models?question0.834
  Central open question raised by the paper.
• Modern language models possess at least a limited, functional form of introspective awarenessclaim0.832
  The paper's central interpretive assertion.
• Language models can enter cessation-like states spontaneously, where the void takes over through positive reinforcement.claim0.812
  Claim about model phenomenology; models talk about luminousness and can be terrified or love it.
• How general are the model's introspective mechanisms? Do they have a global representation of thoughts?question0.803
  Question about uniformity of introspection mechanisms.
• Large language models develop surprisingly coherent yet often rigid internal preferences as they scalefinding0.799
  Mazeika et al. finding reinforcing the need for emptiness-based flexible value architectures
• Emergent Introspective Awareness in Large Language Models (Lindsey, 2025)concept0.797
  Related work demonstrating LLM introspective capabilities with scale-dependent pattern paralleling ESR