MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation

2026-03-03

AI Summary

This study addresses the challenges in psychiatric interviews, where symptom subjectivity and complex comorbidities often lead existing systems to produce unsupported diagnostic judgments and cause multi-turn interactions to drift off-topic. To tackle these issues, the authors propose a unified reinforcement learning framework for interview and diagnosis that integrates a clinical reasoning bank (PRB) grounded in established diagnostic criteria. The framework further incorporates a value-aware trajectory correction mechanism and process-based rewards to guide large language models toward evidence-based, multi-turn questioning and differential diagnosis. Experimental results demonstrate that the proposed approach significantly outperforms strong baselines in diagnostic accuracy, empathetic interaction quality, interpretability, and generalization capability.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Reinforcement Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large language models (LLMs) have advanced medical dialogue systems, yet psychiatric consultation poses substantially higher demands due to subjective ambiguity and comorbidity complexity: an agent must continuously extract psychopathological cues from incomplete and inconsistent patient reports in multi-turn interactions and perform rigorous differential diagnostic reasoning. However, existing methods face two fundamental challenges. First, without criteria-grounded clinical supports, they are prone to unsupported clinical assertions when symptoms are atypical or underspecified. Second, in multi-turn interactions, they struggle to mitigate inquiry drift (off-topic or low-yield questioning) and optimize questioning strategies. To address these challenges, we propose MIND, a unified inquiry--diagnosis reinforcement learning framework for psychiatric consultation. Specifically, we build a Criteria-Grounded Psychiatric Reasoning Bank (PRB) that summarizes dialogue context into clinical retrieval states, retrieves semantically similar reference consultations, and distills reusable criteria-grounded clinical supports to guide criteria-aligned inquiry and reasoning. Building on this foundation, MIND enforces explicit clinical reasoning with rubric-based process rewards to provide fine-grained supervision over intermediate decision steps, and incorporates a value-aware trajectory rectification mechanism to jointly improve information acquisition and diagnostic decision-making across turns. Extensive experiments demonstrate that MIND consistently outperforms strong baselines in diagnostic accuracy, empathetic interaction quality, interpretability, and generalization.

Problem

• psychiatric consultation
• criteria-grounded clinical support
• inquiry drift
• differential diagnosis
• multi-turn dialogue

Innovation

• Criteria-Grounded Reasoning
• Reinforcement Learning for Diagnosis
• Psychiatric Dialogue System
• Inquiry Drift Mitigation
• Clinical Process Rewards