concept
active
concept:model-selection

model selection

Comparing models using log-evidence approximated by free energy.

Neighborhood — ranked by edge-count

Concepts (1)

concept

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.

  • modelconcept0.837
    A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
  • Preference Modelframework0.824
    A model trained on comparison data to assign scores to responses, used as reward signal in RLHF/RLAIF.
  • Analogy between evolution (model selection) and Bayesian model reduction; but evolution is not curious or insightful
  • Used as theoretical motivation for UCCT's log k budget term as complexity penalty mirroring model selection
  • Model Steeringconcept0.787
    Using interventions to guide model generation behavior, e.g., adding sentiment vectors at inference time
  • Selectivitymethod0.787
    Adapted control task metric measuring difference between odds-ratio on original task and arbitrary-label control task
  • Model Editingconcept0.784
    Technique for modifying model knowledge or behavior via targeted interventions, e.g., ROME by Meng et al.
  • Action Selectionconcept0.783
    Choice of policies minimizing expected free energy to realize preferred future states.