Alternative segmentation strategies (phrase-level, information-level, discourse-level) could more effectively capture nuanced intra-sentence inconsistencies than sentence-level atomization

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

• Nucleus sampling generates more semantically diverse utterances than beam searchclaim0.766
  New semantic diversity dimension added to prior finding that nucleus sampling is more lexically diverse
• We hypothesize that native self-report, fine-tuned introspection models, and trained activation-to-language systems will show different performance on bias-resistant localization and strength benchmarkshypothesis0.746
  Comparative prediction motivating future work contrasting different approaches to LLM self-knowledge
• A question anywhere along the line that elicits a premature attempt at an answer could neutralize the remainder of the process into rationalization.hypothesis0.745
  About chain-of-thought and process safety.
• Abstract nouns elicit the highest introspective awareness rates; all concept categories show nonzero detectionfinding0.744
  Opus 4.1 is most effective at recognizing injected abstract concepts (e.g., justice, peace) but detects other categories too.
• Multiscale systems like those prevalent in biology are capable of organizing into complex patterns, whereas rudimentary language models are challenged by long sequences of outputs.claim0.739
  Conclusion about why biology organizes complexity well and flat LLMs do not
• The inability for autoregressive large language models to maintain states of long-range order resembles tangential speech or derailment in formal thought disorder.claim0.738
  Analogy between LLM incoherence and schizophrenia symptoms
• It's tricky, because for a typical language model the entity is sort of tricameral: the base simulator, the simulated simulator, and the simulated awareness.quote0.736
  Antra's earlier definitive statement of the tricameral model.
• More capable models benefit more from Verbalized Sampling, showing an emergent scaling trendclaim0.736
  Empirical observation that larger models (GPT-4.1, Gemini-2.5-Pro) show 1.5-2x greater diversity gains from VS compared to smaller models