Synthetic or Authentic? Building Mental Patient Simulators from Longitudinal Evidence
This work addresses the challenge of creating realistic and diverse patient simulators for mental health dialogue systems, which is incremental as it builds on existing simulation methods by incorporating longitudinal evidence.
The paper tackles the problem of limited profile information and incoherent disease progression in mental health patient simulators by proposing DEPROFILE, a framework that integrates multi-source data to build comprehensive patient profiles, resulting in improved dialogue realism, behavioral diversity, and event richness that exceed state-of-the-art baselines.
Patient simulation is essential for developing and evaluating mental health dialogue systems. As most existing approaches rely on snapshot-style prompts with limited profile information, homogeneous behaviors and incoherent disease progression in multi-turn interactions have become key chellenges. In this work, we propose DEPROFILE, a data-grounded patient simulation framework that constructs unified, multi-source patient profiles by integrating demographic attributes, standardized clinical symptoms, counseling dialogues, and longitudinal life-event histories from real-world data. We further introduce a Chain-of-Change agent to transform noisy longitudinal records into structured, temporally grounded memory representations for simulation. Experiments across multiple large language model (LLM) backbones show that with more comprehensive profile constructed by DEPROFILE, the dialogue realism, behavioral diversity, and event richness have consistently improved and exceed state-of-the-art baselines, highlighting the importance of grounding patient simulation in verifiable longitudinal evidence.