Inference-Time Intervention (ITI)

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

• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model (Li et al., 2023)concept0.820
  Safety intervention that relies on activation modification, which ESR might undermine
• Inference-Time Steeringconcept0.800
  Subtracting a scaled persona vector from hidden states at each decoding step to reduce trait expression after finetuning
• Inference-Time Controlconcept0.797
  Approach to steering LLM behavior without modifying weights, offering flexibility and composability
• Inference-Time Scalingconcept0.784
  Paradigm of improving model outputs through more computation at inference time; VS is presented as a diversity-oriented alternative
• perceptual inferenceconcept0.746
  The process of inferring causes of sensory inputs, a key aspect of the free-energy minimization scheme.
• Stages of Inferenceframework0.738
  The perspective that LLM inference decomposes into distinct computational stages, which the paper extends to looped models
• inference of sentienceconcept0.729
  Attributing subjective experience based on observable embodied behaviours.
• Interchange Intervention Accuracy (IIA) Metricmethod0.718
  Metric measuring accuracy of DNN under intervention at matching algorithm-predicted outputs on held-out test set