An evidence-guided reinforcement learning method to improve psychiatric reasoning in small language models

The paper introduces ClinMPO, an evidence‑guided reinforcement‑learning framework that enhances psychiatric reasoning in small language models (SLMs). ClinMPO leverages a reward model (ClinRM) trained on 18,569 question–answer pairs from 4,474 psychiatry articles and is guided by the psychiatrist‑defined Clinical Psychiatry Thinking Strategy (CPTS). Evaluations on four Qwen3 model sizes show that ClinMPO outperforms baseline, supervised fine‑tuning, and standard policy optimization, with the 8B model surpassing a human baseline of senior pre‑licensure medical students and achieving the highest rank among 31 models. Blinded clinician assessment confirms improved rationale quality across CPTS criteria, demonstrating that clinical evidence and specialist knowledge can be effectively incorporated into medical AI development.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• reinforcement-learning
• fine-tuning
• safety