Do findings from multiple-choice question or short-form evaluation of persona fidelity generalize to open-ended generation tasks?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• The model-persona view crucially depends on Hypothesis 3; without discrete persona regions, the simulator view is more aptclaim0.776
  Identifies the key theoretical vulnerability of the model-persona view
• In 100-300 word generation tasks, generation length does not substantially degrade persona fidelity at the atomic levelclaim0.774
  Contradicts prior concern that longer generations cause coherence degradation
• Persona alignment improves when the model is exposed to contextual cues explicitly relevant to the assigned persona, as in structured questionnaire tasksclaim0.770
  Supported by GPT-4o achieving highest ACCatom in Questionnaire vs Essay and SMP tasks
• Hypothesis 2 (Persona Space): Persona vectors jointly compose a persona space; an instance's general dispositional profile is specified by a combination of activations along multiple persona vectorshypothesis0.762
  Second of three hypotheses about persona implementation, supported by PCA evidence from Lu et al.
• A linear preference vector encoding how much a model likes a given task is persona-relative: it activates strongly for creative writing in the assistant but for phishing in the evil personafinding0.755
  Evidence that core representations like preferences are persona-relative, supporting claim that personas gate content of representations
• A single direction encoding whether the model represents a claim as true or false is persona-relative across conversations (Lampinen et al. 2026)finding0.754
  Additional evidence that core representations are persona-relative, supporting Claim about persona-relative representations
• The model is able to express many subforms of a persona, with different elicitation methods eliciting different manifestationshypothesis0.754
  PSM-derived hypothesis supported by discourse-type facet analysis
• There may exist a natural 'persona basis' characterizing the space of all model personas, with correlations between persona vectors predicting co-expression of traitshypothesis0.753
  Open question proposed by authors for future work on the dimensionality and structure of persona space