# MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis

arXiv: https://arxiv.org/abs/2602.03340 · HTML: https://mlsanity.com/paper/2602.03340/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 20 of its 53 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 20 of 20)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions](https://mlsanity.com/paper/1806.05258/) (2018)
- [Baichuan-M2: Scaling Medical Capability with Large Verifier System](https://mlsanity.com/paper/2509.02208/) (2025)
- [Early science acceleration experiments with GPT-5](https://mlsanity.com/paper/2511.16072/) (2025)
- [D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat](https://mlsanity.com/paper/2205.11764/) (2022)
- [Anthropic Economic Index report: Uneven geographic and enterprise AI adoption](https://mlsanity.com/paper/2511.15080/) (2025)
- [Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning](https://mlsanity.com/paper/2508.10848/) (2025)
- [CRADLE Bench: A Clinician-Annotated Benchmark for Multi-Faceted Mental Health Crisis and Safety Risk Detection](https://mlsanity.com/paper/2510.23845/) (2025)
- [ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model](https://mlsanity.com/paper/2504.09421/) (2025)
- [The First MPDD Challenge: Multimodal Personality-aware Depression Detection](https://mlsanity.com/paper/2505.10034/) (2025)
- [PsychiatryBench: A Multi-Task Benchmark for LLMs in Psychiatry](https://mlsanity.com/paper/2509.09711/) (2025)
- [PsychBench: A comprehensive and professional benchmark for evaluating the performance of LLM-assisted psychiatric clinical practice](https://mlsanity.com/paper/2503.01903/) (2025)
- [MindSET: Advancing Mental Health Benchmarking through Large-Scale Social Media Data](https://mlsanity.com/paper/2511.20672/) (2025)
- [LLM Assistance for Pediatric Depression](https://mlsanity.com/paper/2501.17510/) (2025)
- [A Baseline for Self-state Identification and Classification in Mental Health Data: CLPsych 2025 Task](https://mlsanity.com/paper/2504.14066/) (2025)

## Built on by (most cited first, 1 of 1)

- [MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters](https://mlsanity.com/paper/2607.08257/) (2026)

## Abstract (arXiv)

Mental health disorders represent a burgeoning global public health challenge. While Large Language Models (LLMs) have demonstrated potential in psychiatric assessment, their clinical utility is severely constrained by benchmarks that lack ecological validity and fine-grained diagnostic supervision. To bridge this gap, we introduce MentalDx Bench, the first benchmark dedicated to disorder-level psychiatric diagnosis within real-world clinical settings. Comprising 712 de-identified electronic health records annotated by board-certified psychiatrists under ICD-11 guidelines, the benchmark covers 76 disorders across 16 diagnostic categories. Evaluation of 18 LLMs reveals a critical textitparadigm misalignment: strong performance at coarse diagnostic categorization contrasts with systematic failure at disorder-level diagnosis, underscoring a gap between pattern-based modeling and clinical hypothetico-deductive reasoning. In response, we propose MentalSeek-Dx, a medical-specialized LLM trained to internalize this clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning. Experiments on MentalDx Bench demonstrate that MentalSeek-Dx achieves state-of-the-art (SOTA) performance with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis.