framework
active
framework:big-two-modelBig Two Model
Meta-trait model grouping OCEAN traits into stability (C, A, reversed N) and plasticity (E, O); used to evaluate covariance patterns from injections
Neighborhood — ranked by edge-count
Papers (1)
paper
Thinkers (2)
thinker
- Colin G DeYoungintroducesCo-author of Big Two model of latent metatraits (stability and plasticity)
- John M DigmanintroducesIntroduced higher-order factors of the Big Five (Big Two)
Concepts (2)
concept
- Cross-Trait Leakageassociated_withUnintended movement of non-target OCEAN traits when steering toward a target trait; quantified via lambda metric
- Stability and Plasticity MetatraitsimplementsTwo latent metatraits predicted by Big Two model: stability (C, A, reversed N) and plasticity (E, O)
Claims (1)
claim
- Interpretive conclusion from Big Two mismatch finding; tentative due to only 46.15% match rate
Findings (1)
finding
- Suggests a gap between LLM learned representations and human personality structure as described by Big Two
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.
- A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
- Theme issue context: relates to internal models of environment, central to consciousness and cognition across substrates.
- One of three model systems studied to analyze free-energy scaling and domain-wall formation in self-organizing systems.
- Pezzulo and Levin's framework for explanation and control of complex living systems above the molecular level, cited as prior work by Levin
- The joint distribution over events in the world that generate observed data; the proposed endpoint of representational convergence
- Primary test domain for manifold steering, including reasoning and ICL tasks
- Transformer-based models like GPT-4, LaMDA, PaLM; assessed for GWT indicators.