method
active
method:correction-probe

Correction probe

Reward probe grading correction interventions (5-class).

Neighborhood — ranked by edge-count

Frameworks (1)

framework

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.

  • Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
  • Causal transformer probe predicting whether a token is in the same Entity as its predecessor.
  • Probesconcept0.803
    Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
  • Probingmethod0.789
    Standard interpretability technique used to read feature beliefs.
  • The adaptive, incremental nature of living process, allowing small steps with continuous evaluation and adjustment.
  • Joint firing raises TPR at slightly higher FPR.
  • Self-Correctionconcept0.776
    Reasoning pattern where model reverses a compliance tendency and returns toward refusal, associated with better safety in QwQ-32B
  • Retraction probemethod0.773
    Reward probe grading retraction interventions.