concept
active
concept:self-correction-data-mixing-ratioSelf-Correction Data Mixing Ratio
Experimental variable sweeping proportion of self-correction to normal response training examples from 10% to 90%
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.
- Fine-tuning on Claude-generated self-correction examples with loss masking to induce ESR-like behavior
- Technique using internal model representations as feedback loops to steer diffusion-based materials generation toward target properties.
- Framework by Lee et al. explaining self-correction via linear latent concept directions, closely related prior work.
- Asserts that the method maintains efficiency across a range of constraint strengths without degradation.
- Prior self-evolving agent method iteratively improving outputs through self-feedback
- A method introduced in Book 1 where observers compare their feeling of self with the life in a candidate thing; Alexander claims it correlates with observed life in thousands of centers.
- The ability of reasoning LLMs to review and revise previous reasoning steps during inference
- Related capability where LLMs correct their own outputs, studied via linear representations.