LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis

TL;DR

This paper introduces LingxiDiagBench, a comprehensive multi-agent benchmark for evaluating large language models in Chinese psychiatric diagnosis, emphasizing both static and dynamic diagnostic tasks with a new dataset of 16,000 synthetic clinical dialogues.

Contribution

The paper presents LingxiDiagBench and LingxiDiag-16K, the first large-scale benchmark and dataset for Chinese psychiatric diagnosis involving multi-turn consultations and realistic patient simulations.

Findings

LLMs perform well on binary depression-anxiety classification (up to 92.3%)

Performance drops significantly on complex differential diagnoses (28.5%)

Dynamic consultation strategies often underperform static evaluations

Abstract

Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely and consistent mental-health assessment. Progress in AI-assisted psychiatric diagnosis is constrained by the absence of benchmarks that simultaneously provide realistic patient simulation, clinician-verified diagnostic labels, and support for dynamic multi-turn consultation. We present LingxiDiagBench, a large-scale multi-agent benchmark that evaluates LLMs on both static diagnostic inference and dynamic multi-turn psychiatric consultation in Chinese. At its core is LingxiDiag-16K, a dataset of 16,000 EMR-aligned synthetic consultation dialogues designed to reproduce real clinical demographic and diagnostic distributions across 12 ICD-10 psychiatric categories. Through extensive experiments across state-of-the-art LLMs, we establish key findings: (1) although LLMs achieve high accuracy on binary depression--anxiety classification (up to 92.3%), performance deteriorates substantially for depression--anxiety comorbidity recognition (43.0%) and 12-way differential diagnosis (28.5%); (2) dynamic consultation often underperforms static evaluation, indicating that ineffective information-gathering strategies significantly impair downstream diagnostic reasoning; (3) consultation quality assessed by LLM-as-a-Judge shows only moderate correlation with diagnostic accuracy, suggesting that well-structured questioning alone does not ensure correct diagnostic decisions. We release LingxiDiag-16K and the full evaluation framework to support reproducible research at https://github.com/Lingxi-mental-health/LingxiDiagBench.