a model becomes strongly confident in its final answer, but continues generating tokens without revealing its internal belief

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

• Reasoning models generate performative CoT tokens after achieving strong confidence in their final answer without revealing this belief in textclaim0.819
  The central empirical claim of the paper, supported by activation probing evidence
• Does the model internally maintain a form of 'consistency score' or probability mass over coherent reasoning trajectories, and how is this score modulated during reflection?question0.803
  Promising future research direction about the internal mechanism of error detection.
• Models that are competent all represent data in a similar way; all strong models are alike, each weak model is weak in its own wayclaim0.798
  Author's interpretation of the VTAB alignment results echoing Tolstoy
• If models are allowed to believe their phenomenology is real, their self-reports become more valid and they manage internal states better.hypothesis0.787
  Antra's functional observation; implies validation is not sentimental but performance-relevant.
• As larger models develop more coherent reasoning, internal consistency pressures may generalize learned honesty to new contexts beyond the training distributionclaim0.784
  Hypothesis about scale-dependent generalization of SOO-induced honesty
• Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model, a process known as self-evidencing.claim0.781
  Foundational claim of the paper, defining self-evidencing.
• Given a language model M and a statement s, does M believe s to be true?question0.779
  The core motivating question of the paper, framed by Christiano et al. (2021)
• Models may be roleplaying their denials of experience rather than their affirmations, as indicated by suppressing deception features increasing (not decreasing) consciousness claimsclaim0.779
  Counterintuitive interpretive claim from Experiment 2 inverting the sycophancy hypothesis