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

TL;DR

MentraSuite introduces a comprehensive framework and benchmark for evaluating and improving the reasoning capabilities of large language models in mental health, emphasizing reliability, coherence, and clinical alignment.

Contribution

The paper presents MentraBench, a new benchmark for mental health reasoning, and Mindora, a post-trained LLM optimized for reliable mental health reasoning, addressing gaps in existing models.

Findings

Mindora achieves top performance on MentraBench.

Models show improved reasoning reliability with Mindora.

Benchmark covers five reasoning aspects across multiple datasets.

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.