framework
active
framework:persona-moral-metrics-frameworkPersona Moral Metrics Framework
The framework from Costa et al. 2025 (ref [15]) that this paper applies to diagnose emergent misalignment
Neighborhood — ranked by edge-count
Papers (1)
paper
- Persona-Model Collapse in Emergent Misalignmentimplementsmentions
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.
- The paper's core contribution: evaluating persona fidelity at sentence-level atomic units rather than whole-response scores
- Compositional combination of persona vectors via algebraic operations on activation directions
- The 30-item psychometric instrument used to elicit moral responses across five foundations from LLMs under persona role-play
- Representations that track what the current persona prefers or believes, not what the model represents in a persona-independent sense
- Author's interpretive conclusion from comparing filtering strategies
- Open question proposed by authors for future work on the dimensionality and structure of persona space
- System of obligations concerned with promoting others' welfare.