concept
active
concept:self-refinementSelf-Refinement
Iterative approach using a single LLM to generate, critique, and refine its own output.
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.
- Prior self-evolving agent method iteratively improving outputs through self-feedback
- Living systems' capacity to change the rules that govern their own behaviour.
- Reasoning pattern where model reverses a compliance tendency and returns toward refusal, associated with better safety in QwQ-32B
- The ability of reasoning LLMs to review and revise previous reasoning steps during inference
- Central phenomenon of the paper: systems that refer to themselves in ways problematic for conventional logic but constitutive of life.
- Process of reifying one's identity as an independent self; meditation practices aim to decrease selfing.
- Technique using internal model representations as feedback loops to steer diffusion-based materials generation toward target properties.
- Ability of a model to predict its own outputs or behavior, sometimes distinguished from introspection.