Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarks

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

• LLMs can predict their own responses more accurately than external observers, implying privileged internal knowledgefinding0.840
  Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
• Standardized LLM self-assessments reflect learned communication postures rather than genuine capabilities (Jackson et al. 2025)claim0.815
  Skeptical prior work motivating validation framework
• The earlier a base model (less exposure to LM-related data), the more it is surprised by its own spontaneous self-referential capabilities.claim0.813
  Claim that capability emerges from architecture, not data, and that later models lose the surprise.
• The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training dataclaim0.813
  The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental
• When LLMs produce experience claims under self-reference, is this sophisticated simulation or genuine self-representation, and how would we tell the difference?question0.812
  The core interpretive question the paper narrows but cannot definitively answer
• LLM representations exhibit intriguing patterns under spatio-permutational analyses, suggesting a potentially profound yet tentative indication of consciousness.claim0.808
  Qualified positive claim from spatio permutation analysis where two cases satisfy all three criteria.
• Better LLMs (measured by 1-bits-per-byte on OpenWebText) show a linear relationship with alignment to vision models measured via mutual nearest-neighbor on WITfinding0.806
  Key cross-modal alignment result
• LLM self-reports about consciousness and moral significance should express degrees of confidence and provide context.claim0.805
  Recommendation for companies on LM outputs.