Soft preference labels

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Softmax policy selectionmethod0.741
  Selecting policies using a softmax (normalized exponential) function of negative expected free energy.
• Inexpensive Preferencesconcept0.733
  Designing digital minds to have preferences that are trivially easy to satisfy, yielding high welfare at minimal resource cost
• Preference Conflictconcept0.727
  Key element for alignment faking: model's pre-existing preferences contradict the new training objective
• Preference Strengthconcept0.726
  The problematic possibility of digital minds with superhumanly strong preferences requiring interpersonal utility comparison frameworks
• Preference Learningconcept0.716
  The ability of active inference agents to learn their own prior preferences over outcomes by accumulating Dirichlet parameters from experience.
• Preference Modelframework0.714
  A model trained on comparison data to assign scores to responses, used as reward signal in RLHF/RLAIF.
• Prior Preferencesconcept0.709
  Target distribution over states or outcomes encoded in the generative model; goal states.
• Prior Preferences over Outcomesconcept0.703
  Replaces explicit reward signal in active inference; encodes agent's preferred observations independent of environment.