Saved in:
Bibliographic Details
Main Authors: Zhang, Xinyuan, Wang, Zijian, Dao, Chang, Zhou, Juexiao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.09216
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917203364806656
author Zhang, Xinyuan
Wang, Zijian
Dao, Chang
Zhou, Juexiao
author_facet Zhang, Xinyuan
Wang, Zijian
Dao, Chang
Zhou, Juexiao
contents Data scarcity and unreliable self-reporting -- such as concealment or exaggeration -- pose fundamental challenges to psychiatric intake and assessment. We propose a multi-agent synthesis framework that explicitly models patient deception to generate high-fidelity, publicly releasable synthetic psychiatric intake records. Starting from DAIC-WOZ interviews, we construct enriched patient profiles and simulate a four-role workflow: a \emph{Patient} completes self-rated scales and participates in a semi-structured interview under a topic-dependent honesty state; an \emph{Assessor} selects instruments based on demographics and chief complaints; an \emph{Evaluator} conducts the interview grounded in rater-administered scales, tracks suspicion, and completes ratings; and a \emph{Diagnostician} integrates all evidence into a diagnostic summary. Each case links the patient profile, self-rated and rater-administered responses, interview transcript, diagnostic summary, and honesty state. We validate the framework through four complementary evaluations: diagnostic consistency and severity grading, chain-of-thought ablations, human evaluation of clinical realism and dishonesty modeling, and LLM-based comparative evaluation. The resulting corpus spans multiple disorders and severity levels, enabling controlled study of dishonesty-aware psychiatric assessment and the training and evaluation of adaptive dialogue agents.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09216
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Honesty-Aware Multi-Agent Framework for High-Fidelity Synthetic Data Generation in Digital Psychiatric Intake Doctor-Patient Interactions
Zhang, Xinyuan
Wang, Zijian
Dao, Chang
Zhou, Juexiao
Databases
Data scarcity and unreliable self-reporting -- such as concealment or exaggeration -- pose fundamental challenges to psychiatric intake and assessment. We propose a multi-agent synthesis framework that explicitly models patient deception to generate high-fidelity, publicly releasable synthetic psychiatric intake records. Starting from DAIC-WOZ interviews, we construct enriched patient profiles and simulate a four-role workflow: a \emph{Patient} completes self-rated scales and participates in a semi-structured interview under a topic-dependent honesty state; an \emph{Assessor} selects instruments based on demographics and chief complaints; an \emph{Evaluator} conducts the interview grounded in rater-administered scales, tracks suspicion, and completes ratings; and a \emph{Diagnostician} integrates all evidence into a diagnostic summary. Each case links the patient profile, self-rated and rater-administered responses, interview transcript, diagnostic summary, and honesty state. We validate the framework through four complementary evaluations: diagnostic consistency and severity grading, chain-of-thought ablations, human evaluation of clinical realism and dishonesty modeling, and LLM-based comparative evaluation. The resulting corpus spans multiple disorders and severity levels, enabling controlled study of dishonesty-aware psychiatric assessment and the training and evaluation of adaptive dialogue agents.
title Honesty-Aware Multi-Agent Framework for High-Fidelity Synthetic Data Generation in Digital Psychiatric Intake Doctor-Patient Interactions
topic Databases
url https://arxiv.org/abs/2601.09216