concept
active
concept:l-retain-loss-term

L_retain Loss Term

Regularization component of the composite loss that penalizes deviation from baseline model behavior on Alpaca instructions

Neighborhood — ranked by edge-count

Methods (1)

method

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.

  • Modified CL Lossframework0.737
    Novel variant of CL loss introduced in this paper targeting only causal subspace dimensions to improve OOD performance
  • Loss Functionconcept0.726
    In machine learning, a function measuring the distance between current and desired output; analogous to stress.
  • Auxiliary training objective from Grant (2025) that constrains intervened representations to remain near natural distribution
  • Addressing disparity in loss magnitudes across tasks at the loss level
  • Loss of feelingconcept0.697
    The deadening effect of modern processes that prevent people from acting according to their feeling for the whole, damaging the global whole.
  • Auxiliary objective combining L2 and cosine losses against pre-recorded CL vectors to improve causal relevance when one model is causally inaccessible.
  • Additional term in RL SOO loss preserving agent capabilities analogous to KL term in RLHF
  • InfoNCE Lossmethod0.694
    One of two contrastive objectives analyzed; shown to be minimized by PMI kernel representation up to scaling