Neutral Prediction

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

• Neutral NLI predictions may capture lexical rather than semantic diversityhypothesis0.775
  Hypothesis proposed to explain Neutral NLI Diversity's high performance on decTest but low on conTest
• Contradiction Predictionconcept0.774
  NLI class indicating two sentences are semantically incompatible; weighted +1 in NLI Diversity scoring
• Normative predictionsconcept0.768
  In active inference, predictions about what should be, held to motivate action; overflow leads to tanha.
• Prediction Errorconcept0.766
  Role in optimizing sensory states; unified treatment shows value-learning and perception share error-minimization principle.
• What is the role of neutral NLI predictions in measuring semantic diversity?question0.763
  Motivates the creation of Neutral NLI Diversity as an ablation
• zero-shot predictionconcept0.751
  Prediction without task-specific training; Evee achieves 0.991 AUROC on indels in zero-shot mode.
• Next-Token Prediction (NTP)method0.749
  Training objective used for all neural network models in the paper; cross-entropy loss over predicted token sequences.
• Goal-Relative Prediction Errorconcept0.736
  The signed directional computation of how actual outcomes compare to goal-specified targets; identified with valence