concept
active
concept:model-evidence

Model Evidence

Probability of data under the model, penalizing complexity and rewarding accuracy.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • The probability of sensory data under a generative model; negative log evidence is bounded by free energy.

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.

  • modelconcept0.842
    A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
  • Model Deceptionconcept0.825
    LLM behavior of generating falsehoods; the multi-dimensional truth subspace raises new risks for subtle manipulation
  • Reasoning Modelsconcept0.812
    Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper
  • Reasoning modelconcept0.803
    Models like R1 that produce chain-of-thought and backtrack; claimed qualitatively different from non-reasoning LMs.
  • Formal Modelmethod0.789
  • Model-persona viewframework0.787
    New view introduced by this paper: a mind is the union of all instance-persona segments that activate the same persona region of a given model
  • Proposal for standard studied networks akin to Drosophila.
  • model selectionconcept0.780
    Comparing models using log-evidence approximated by free energy.