concept
active
concept:contrastive-promptingContrastive Prompting
Technique for extracting trait directions by contrasting model activations under trait-eliciting vs. trait-suppressing conditions
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Adaptation of instruction-tuned extraction to base models using third-person descriptions and hypothetical situations
- The baseline prompting method asking for a single response (e.g., 'Tell me a joke about coffee'), which suffers from mode collapse
- Established baseline for OCEAN steering via personality-descriptive system prompts; compared against injection methods throughout
- LAT methodology step constructing paired prompts that elicit divergent behaviors to extract steering vectors
- Training method for probes: generate completions under opposing system prompts to induce positive and negative poles of a concept
- 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
- The property that living structures contain intense contrast—far more than one imagines helpful; true opposites which annihilate each other when superimposed, creating differentiation that gives birth to something; contrast unifies rather than separates when used correctly