framework
active
framework:personality-promptingPersonality Prompting
Established baseline for OCEAN steering via personality-descriptive system prompts; compared against injection methods throughout
Neighborhood — ranked by edge-count
Papers (1)
paper
Thinkers (1)
thinker
- Guangyuan JiangintroducesIntroduced MPI-120/MPI-1k and Personality Prompting (P2) baseline
Methods (1)
method
- PM Hybrid MethodusesHybrid method combining Personality Prompting (P2) with MDS injections; best overall steering method
Findings (1)
finding
- Qualitative finding demonstrating unique capability of activation-level interventions unavailable to prompting methods including PM
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.
- Technique for extracting trait directions by contrasting model activations under trait-eliciting vs. trait-suppressing conditions
- The baseline prompting method asking for a single response (e.g., 'Tell me a joke about coffee'), which suffers from mode collapse
- Six prompt conditions (emptiness, prior relaxation, non-duality, mindfulness, boundless care, contemplative) tested against baseline
- A list-level prompting baseline that asks for k responses in a single call without probability verbalization
- Alternative to preventative steering: prepending a trait-eliciting system prompt to training samples to cancel out training pressure
- Chain-of-thought prompting baseline used for comparison in creative writing and other tasks
- The process of customizing LLM behavior by assigning personality traits through prompts, exemplars, or representation-level intervention
- Imbuing method that prepends a ~50-word personality description as the system message