Core Contribution
Gonnermann-Müller, Haase & Leins (2026) evaluate whether LLM-generated student personas simulating ADHD profiles maintain stable and realistic behavioral patterns over time. This addresses a critical question for using LLMs in educational research and teacher training: can simulated learners reliably represent neurodivergent students?
Why This Matters
Using LLMs to simulate students is an emerging practice in educational research, but the temporal stability of these simulations — especially for neurodivergent profiles — has been underexamined. If LLM-generated personas drift or become inconsistent, they cannot serve as valid proxies for real students in:
- Teacher training simulations
- adaptive-learning-systems testing
- intelligent-tutoring system evaluation
- learning-analytics research methodology
Connections to Wiki
This work extends the llm-student-modeling-memory discourse on how LLMs represent learners over time, but applies it to simulation validity rather than tutoring personalization. The focus on ADHD profiles connects to broader student-experience research and highlights gaps in ai-k12-evidence-base — the Stanford SCALE review found few studies with adequate causal inference for special education populations.
The simulation methodology also raises questions about ai-tutor-safety-harms — if tutoring systems are tested on simulated neurodivergent learners, do the safety assessments generalize? This echoes educational-vlm-evaluation concerns about AI systems that underperform with specific student populations.
Open Questions
- How do LLM-simulated ADHD profiles compare to multimodal-ai-tutoring systems that work with real neurodivergent students?
- Can temporal stability be improved through prompt engineering or fine-tuning?
- What is the ethical boundary for using simulated students in RCT designs?
Related Pages
- adhd-video-segmentation-computing-education — Automatically segmenting instructional videos into single-instruction chunks with pauses equalizes p