concept
active
concept:self-correction

Self-Correction

Reasoning pattern where model reverses a compliance tendency and returns toward refusal, associated with better safety in QwQ-32B

Neighborhood — ranked by edge-count

Related by similarity (8)

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.

  • Technique using internal model representations as feedback loops to steer diffusion-based materials generation toward target properties.
  • Related capability where LLMs correct their own outputs, studied via linear representations.
  • Selfingconcept0.833
    Process of reifying one's identity as an independent self; meditation practices aim to decrease selfing.
  • Fine-tuning on Claude-generated self-correction examples with loss masking to induce ESR-like behavior
  • Self-Modificationconcept0.827
    Living systems' capacity to change the rules that govern their own behaviour.
  • Self-Referenceconcept0.818
    Central phenomenon of the paper: systems that refer to themselves in ways problematic for conventional logic but constitutive of life.
  • The adaptive, incremental nature of living process, allowing small steps with continuous evaluation and adjustment.
  • Experimental variable sweeping proportion of self-correction to normal response training examples from 10% to 90%