method
active
method:counterfactual-prediction-trainingCounterfactual prediction training
Training models to answer Yes/No whether a prompt edit changes their behavior.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Model explains its own behavior without implying introspection.
Methods (2)
method
- Counterfactual reflection trainingrelated_toFine-tuning on reflection turns to implant principles into workspace.
- KL penalty to base model so self-explanation stays about the same model.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Ability to entertain competing hypotheses within one inference engine; proposed hallmark of mindful inference
- Encoding possible future or alternative states; bioelectric patterns can represent an alternative morphological target even in an intact animal.
- The behavior that would have occurred had the value of a causal variable been different while everything else remained the same; used as training labels in DAS/MAS.
- The output value a model produces when an interchange intervention forces certain variables to take values from source inputs.
- The mental effort of holding models of how things could/should be different from actuality, contributing to compression stress.
- The state a neural network is placed in when its activations are modified via intervention
- Lens for evaluating explanations by whether they help predict behavior on counterfactual inputs.