concept
active
concept:self-correctionSelf-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
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities 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.
- 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
- Living systems' capacity to change the rules that govern their own behaviour.
- 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%