method
active
method:auxk-auxiliary-loss

AuxK auxiliary loss

Dead-feature revival loss following Gao et al.

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Related by similarity (6)

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.

  • Auxiliary objective combining L2 and cosine losses against pre-recorded CL vectors to improve causal relevance when one model is causally inaccessible.
  • Loss Functionconcept0.668
    In machine learning, a function measuring the distance between current and desired output; analogous to stress.
  • Loss Recoveredmethod0.664
    Reconstruction fidelity score based on cross-entropy.
  • L_retain Loss Termconcept0.659
    Regularization component of the composite loss that penalizes deviation from baseline model behavior on Alpaca instructions
  • Loss on randomly masked subcomponents matching target outputs, with layerwise auxiliary.
  • Modified CL Lossframework0.651
    Novel variant of CL loss introduced in this paper targeting only causal subspace dimensions to improve OOD performance