MentraSuite: Post-Training Large Language Models for Mental Health Reasoning and Assessment

2025/12/10 by Mengxi Xiao, Xiao, Mengxi, Kailai Yang +21
Computer Science · Psychology · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning in Healthcare #Mental Health via Writing #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2512.09636

openalex publication_date 2025/12/10 · openalex created_date 2025/12/12 · openalex updated_date 2026/07/28

Abstract

Mental health disorders affect hundreds of millions globally, and the Web now serves as a primary medium for accessing support, information, and assessment. Large language models (LLMs) offer scalable and accessible assistance, yet their deployment in mental-health settings remains risky when their reasoning is incomplete, inconsistent, or ungrounded. Existing psychological LLMs emphasize emotional understanding or knowledge recall but overlook the step-wise, clinically aligned reasoning required for appraisal, diagnosis, intervention planning, abstraction, and verification. To address these issues, we introduce MentraSuite, a unified framework for advancing reliable mental-health reasoning. We propose MentraBench, a comprehensive benchmark spanning five core reasoning aspects, six tasks, and 13 datasets, evaluating both task performance and reasoning quality across five dimensions: conciseness, coherence, hallucination avoidance, task understanding, and internal consistency. We further present Mindora, a post-trained model optimized through a hybrid SFT-RL framework with an inconsistency-detection reward to enforce faithful and coherent reasoning. To support training, we construct high-quality trajectories using a novel reasoning trajectory generation strategy, that strategically filters difficult samples and applies a structured, consistency-oriented rewriting process to produce concise, readable, and well-balanced trajectories. Across 20 evaluated LLMs, Mindora achieves the highest average performance on MentraBench and shows remarkable performances in reasoning reliability, demonstrating its effectiveness for complex mental-health scenarios.

Citations

• Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
• From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning
• MHQA: A Diverse, Knowledge Intensive Mental Health Question Answering Challenge for Language Models
• HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
• PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling
• Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions
• MHMisinfo - Video-based Mental Health Misinformation Dataset
• Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation
• Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts
• Cognitive Reframing of Negative Thoughts through Human-Language Model Interaction
• PRAG: Paninian Retrieval-Augmented Generation for Safety-Critical Medical Question Answering
• PubMedQA: A Dataset for Biomedical Research Question Answering
• Personalizing Dialogue Agents: I have a dog, do you have pets too?

Related

• Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text
• P-ReMIS: Pragmatic Reasoning in Mental Health and a Social Implication
• ProMind-LLM: Proactive Mental Health Care via Causal Reasoning with Sensor Data
• A Layered Multi-Expert Framework for Long-Context Mental Health Assessments
• Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling