Large Language Models as Simulative Agents for Neurodivergent Adult Psychometric Profiles

TL;DR

This study demonstrates that large language models can simulate neurodivergent psychometric profiles from qualitative interviews, showing promise for research applications but with domain-specific limitations.

Contribution

It introduces a method for using LLMs to generate neurodevelopmental trait responses based on interview data, advancing psychometric simulation capabilities.

Findings

LLMs outperform random responses in simulating psychometric data

GPT-4o shows higher accuracy and reproducibility than Qwen3-235B-A22B

Simulated responses closely match human data for most measures except some subscales

Abstract

Adult neurodivergence, including Attention-Deficit/Hyperactivity Disorder (ADHD), high-functioning Autism Spectrum Disorder (ASD), and Cognitive Disengagement Syndrome (CDS), is marked by substantial symptom overlap that limits the discriminant sensitivity of standard psychometric instruments. While recent work suggests that Large Language Models (LLMs) can simulate human psychometric responses from qualitative data, it remains unclear whether they can accurately and stably model neurodevelopmental traits rather than broad personality characteristics. This study examines whether LLMs can generate psychometric responses that approximate those of real individuals when grounded in a structured qualitative interview, and whether such simulations are sensitive to variations in trait intensity. Twenty-six adults completed a 29-item open-ended interview and four standardized self-report measures (ASRS, BAARS-IV, AQ, RAADS-R). Two LLMs (GPT-4o and Qwen3-235B-A22B) were prompted to infer an individual psychological profile from interview content and then respond to each questionnaire in-role. Accuracy, reliability, and sensitivity were assessed using group-level comparisons, error metrics, exact-match scoring, and a randomized baseline. Both models outperformed random responses across instruments, with GPT-4o showing higher accuracy and reproducibility. Simulated responses closely matched human data for ASRS, BAARS-IV, and RAADS-R, while the AQ revealed subscale-specific limitations, particularly in Attention to Detail. Overall, the findings indicate that interview-grounded LLMs can produce coherent and above-chance simulations of neurodevelopmental traits, supporting their potential use as synthetic participants in early-stage psychometric research, while highlighting clear domain-specific constraints.