community
active
leiden_hybrid_concepts
label: sonnet
community:leiden_hybrid_concepts-run2-c132Contemplative prompting for LLMs
A brief reflective system prompt boosts performance across 28 models by ~2.6 points.
2 members. Each node is clickable.
Loading graph…
Drawn from 2 sources
The papers/notes whose extracted claims & findings make up this cluster.
Bridges (3)
Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.
Findings (2)
- A 337-character contemplative system prompt lifts all 28 models by +2.62 points on a 10-point scale.Core empirical result: every model, every architecture, every alignment type responds to the contemplative prompt with measurable gain.
- Contemplative prompt elevates self-observation task performance in language models.Supports Janus's claim that introspection is architecturally available; prompting determines whether/how capacity is leveraged.