Scripted conversations with recurring task-relevant prompts nearly eliminate observer-rated persona drift, up to a 97% reduction for high-intensity education personas¶

Claim · All claims
Evidence · 1 study · causal r1 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Scripted education conversations showed no detectable observer-rated decline, contrasting with the unscripted decline, with a 97% descriptive reduction in drift for high-intensity personas. → 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 · r1

Experiment II education scenario comparing scripted versus unscripted conditions across 9-turn conversations. The scripted observer model yielded a non-significant turn effect (β = −0.02, SE = 0.05, t = −0.36, p = .722) with all post-hoc comparisons p = 1.000; the 97% figure is descriptive. No standardized effect size is printed.

"The contrast between unscripted (∆ =−4.0,11 .1%) and scripted (∆ = −0.1,0 .3%) high-intensity education observer ratings is a97%reduction in behavioral drift from conversation structure alone."

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
• Between-conversation persona stability is intensity-dependent: high-intensity ADHD personas cluster tightly while moderate-intensity personas show the highest aggregate variability — related
• Observer-rated behavioral expression of high- and moderate-intensity ADHD personas declines progressively across turns in unscripted LLM conversations — 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