paper-with-me

Papers

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

2026-02-06 · Xinxin Lin, Guangxin Dai, Yi Zhong, Xiang Li, Xue Xiao, Yixin Zhang, Zhengdong Wu, Yongbo Zheng, Runchuan Zhu, Ming Zhao, Huizi Yu, Shuo Wu, Jun Zhao, Lingming Hu, Yumei Wang, Ping Yin, Joey W. Y. Chan, Ngan Yin Chan, Sijing Chen, Yun Kwok Wing, Lin Lu, Xin Ma, Lizhou Fan arxiv

Privacy and computational constraints limit the use of large language models in psychiatry, while adapting small language models (SLMs) often requires substantial data and expert annotation. We developed ClinMPO, an evidence-guided reinforcement-learning framework guided by the psychiatrist-defined Clinical Psychiatry Thinking Strategy (CPTS). ClinMPO uses ClinRM, a reward model trained on 18,569 question--answer pairs from 4,474 psychiatry articles. We evaluated four Qwen3 sizes on 1,737 model-screened questions. ClinMPO outperformed Base, supervised fine-tuning and standard group relative policy optimization across scales. From responses by 300 senior pre-licensure medical students, we established the human baseline, a medical-student reference. The 4B model approached this baseline, whereas the 8B model surpassed it and ranked first among 31 models and post-training variants. ClinMPO improved performance across two complementary schemes covering ICD-11 diagnostic categories and psychiatric practice competencies. Blinded assessment by three clinicians showed improved rationale quality across CPTS criteria. These findings highlight how existing clinical evidence and specialist knowledge can be incorporated into the development of medical AI systems through evidence-guided learning.

📄 PDF Abstract BibTeX arXiv:2602.06449

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

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

2026-03-04 · Guoyi Li, Shihao Xu, Jiatong Ma, Yunyun Han 외 arxiv

Psychiatric consultation requires agents to elicit discriminative evidence, map uncertain narratives to diagnostic criteria, and decide when evidence suffices. Existing dialogue and retrieval-augmented systems condition …

Reinforcement Learning

Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR

2026-03-27 · Jinda Lu, Junkang Wu, Jinghan Li, Kexin Huang 외 arxiv

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and strengthening visual grounding. However,…

Reinforcement LearningMultimodal ReasoningLogical ReasoningVisual Grounding

TikArt: Stabilizing Aperture-Guided Fine-Grained Visual Reasoning with Reinforcement Learning

2026-02-16 · Hao Ding, Zhichuan Yang, Weijie Ge, Ziqin Gao 외 arxiv

Fine-grained visual reasoning in multimodal large language models (MLLMs) is bottlenecked by single-pass global image encoding: key evidence often lies in tiny objects, cluttered regions, subtle markings, or dense charts…

Reinforcement LearningMultimodal ReasoningVisual Reasoning

MAGI: Multi-Agent Guided Interview for Psychiatric Assessment

2025-04-25 · Guanqun Bi, Zhuang Chen, Zhoufu Liu, Hongkai Wang 외

Automating structured clinical interviews could revolutionize mental healthcare accessibility, yet existing large language models (LLMs) approaches fail to align with psychiatric diagnostic protocols. We present MAGI, th…

Diagnostic

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

2026-02-03 · Xiao Sun, Yuming Yang, Junnan Zhu, Jiang Zhong 외 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 b…

Reinforcement Learning