method
active
method:inoculation-promptingInoculation Prompting
Prompt explains concept so it is not attributed to the global preference signal.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Unifying framework: remove or amplify a concept's term in the exponential-tilt reward.
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.
- Established baseline for OCEAN steering via personality-descriptive system prompts; compared against injection methods throughout
- The baseline prompting method asking for a single response (e.g., 'Tell me a joke about coffee'), which suffers from mode collapse
- Unifying Bayesian lens.
- Technique for extracting trait directions by contrasting model activations under trait-eliciting vs. trait-suppressing conditions
- Prompting technique where k example pairs are provided as anchors.
- Alternative to preventative steering: prepending a trait-eliciting system prompt to training samples to cancel out training pressure
- Six prompt conditions (emptiness, prior relaxation, non-duality, mindfulness, boundless care, contemplative) tested against baseline
- Assumption that DNN layers preserve input information by being injective; key condition for Theorem 1