Between-conversation persona stability is intensity-dependent: high-intensity ADHD personas cluster tightly while moderate-intensity personas show the highest aggregate variability¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Across independent conversations, both self-reports and observer ratings are more stable at high than moderate intensity in the education scenario. → Jana Gonnermann-Müller 2026

Evidence¶

Jana Gonnermann-Müller 2026¶

Jana Gonnermann-Müller, Jennifer Haase, Nicolas Leins, Thomas Kosch, Sebastian Pokutta. (2026). LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD-Related Persona Specifications. https://arxiv.org/abs/2605.06307 doi:10.48550/arxiv.2605.06307

q2 · i? · causal · r2

Experiment I pooled distributions across 50 independent runs, five models, and three prompt formats in the education scenario. Moderate-intensity self-reports showed higher variability (M = 18.0, SD = 5.04, 14.0% of scale); observer ratings showed the same pattern (high M = 21.1, SD = 2.57; moderate M = 16.6, SD = 4.78). Variability is descriptive; no standardized effect size is printed.

"High-intensity personas produced tight clustering across the pooled observations (education:M = 30.2, SD = 1.79)."

Discussion¶

Related Claims¶

• Default personas show a self-report–behavior gap: they endorse moderate-range ADHD characteristics on self-report while displaying only weakly elevated ADHD-like behavior to observers — related
• Observer-rated behavioral expression of high- and moderate-intensity ADHD personas declines progressively across turns in unscripted LLM conversations — related
• Scripted conversations with recurring task-relevant prompts nearly eliminate observer-rated persona drift, up to a 97% reduction for high-intensity education personas — related
• LLM-simulated students' self-reported ADHD persona scores remain stable throughout extended multi-turn conversations — related
• Model family and prompt format moderate the level of simulated ADHD persona expression — related
• LLM observer ratings converge excellently with human expert judgments in applying the CAARS observer instrument to generated narratives — related