Advancing Psychiatric Diagnosis with Large Language Models: Interpretability, Prompting Strategies and Clinical Applications
: Large Language Models (LLMs) have shown potential to improve psychiatric assessment by addressing limitations in traditional diagnostic methods. This review summarizes recent developments in applying LLMs to mental health evaluation, focusing on three core strategies: questionnaire emulation (e.g., GPT-based PHQ-9/GAD-7), free-text classification of clinical narratives and social media posts, and integrated diagnostic-treatment workflows based on DSM/ICD criteria. Emphasis is placed on prompt engineering techniques — such as chain-of-thought and diagnostic reasoning prompts — that enhance model interpretability by generating stepwise rationales. These methods allow LLMs to mimic clinical reasoning while producing transparent, structured outputs. Empirical studies report high internal consistency and moderate-to-strong agreement with validated tools, along with performance metrics that approach or surpass human baselines in selected tasks. Key challenges include generalization across cultural contexts, explanation fidelity, and clinical applicability. Addressing these issues will require robust prompt design, alignment with clinical guidelines, and validation in real-world settings. This review provides a framework for understanding LLM-based diagnostic methods and outlines directions for future development in computational psychiatry.