Baichuan-M2: Scaling Medical Capability with Large Verifier System

• URL: http://arxiv.org/abs/2509.02208v1
• Date: Tue, 02 Sep 2025 11:23:35 GMT
• Title: Baichuan-M2: Scaling Medical Capability with Large Verifier System
• Authors: Baichuan-M2 Team, :, Chengfeng Dou, Chong Liu, Fan Yang, Fei Li, Jiyuan Jia, Mingyang Chen, Qiang Ju, Shuai Wang, Shunya Dang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Chenzheng Zhu, Da Pan, Fei Deng, Guangwei Ai, Guosheng Dong, Hongda Zhang, Jinyang Tai, Jixiang Hong, Kai Lu, Linzhuang Sun, Peidong Guo, Qian Ma, Rihui Xin, Shihui Yang, Shusen Zhang, Yichuan Mo, Zheng Liang, Zhishou Zhang, Hengfu Cui, Zuyi Zhu, Xiaochuan Wang,
• Abstract summary: We introduce a novel dynamic verification framework that moves beyond static answer verifier.<n>We develop Baichuan-M2, a medical augmented reasoning model trained through a multi-stage reinforcement learning strategy.<n> evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts.
• Score: 40.86227022086866
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language models (LLMs) advance in conversational and reasoning capabilities, their practical application in healthcare has become a critical research focus. However, there is a notable gap between the performance of medical LLMs on static benchmarks such as USMLE and their utility in real-world clinical decision-making. This discrepancy arises because traditional exams fail to capture the dynamic, interactive nature of medical consultations. To address this challenge, we introduce a novel dynamic verification framework that moves beyond static answer verifier, establishing a large-scale, high-fidelity interactive reinforcement learning system. Our framework comprises two key components: a Patient Simulator that creates realistic clinical environments using de-identified medical records, and a Clinical Rubrics Generator that dynamically produces multi-dimensional evaluation metrics. Building on this foundation, we develop Baichuan-M2, a 32B-parameter medical augmented reasoning model trained through a multi-stage reinforcement learning strategy with an improved Group Relative Policy Optimization (GRPO) algorithm. Evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts, achieving a score above 32 on the challenging HealthBench Hard benchmark-previously exceeded only by GPT-5. Our work demonstrates that robust dynamic verifier system is essential for aligning LLM capabilities with practical clinical applications, establishing a new Pareto front in the performance-parameter trade-off for medical AI deployment.

Related papers

• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models [15.91764739198419]
  We present MedDialogRubrics, a novel benchmark comprising 5,200 synthetically constructed patient cases and over 60,000 fine-grained evaluation rubrics.<n>Our framework employs a multi-agent system to synthesize realistic patient records and chief complaints without accessing real-world electronic health records.
  arXiv  Detail & Related papers  (2026-01-06T13:56:33Z)
• Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models [45.285970665585914]
  We propose a comprehensive framework for Continual Learning.<n>We employ a multi-modal, multi-layer RAG system that provides real-time guidance for model fine-tuning.<n>We introduce a dynamic knowledge distillation framework.
  arXiv  Detail & Related papers  (2025-12-15T08:09:40Z)
• Multidimensional Rubric-oriented Reward Model Learning via Geometric Projection Reference Constraints [4.79357178898034]
  We introduce MR-RML (Multidimensional-oriented Reward Model Learning) with GPRC (Geometric Projection Reference Constraints)<n>Our approach introduces three key innovations: (1) a medical standard system that embeds domain-specific guidelines throughout the training pipeline; (2) an independent multi-dimensional reward model that decomposes evaluation criteria; and (3) projection reference constraints that translate clinical cognitive logic into mathematical regularization.<n>Our method significantly boosts the performance of the base Qwen-32B model, with improvements of 45% on the full subset and 85% on the hard subset.
  arXiv  Detail & Related papers  (2025-11-20T08:26:16Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making [4.801722645791233]
  DynamiCare is a novel dynamic multi-agent framework that models clinical diagnosis as a multi-round, interactive loop.<n>We demonstrate the feasibility and effectiveness of DynamiCare through extensive experiments.
  arXiv  Detail & Related papers  (2025-07-03T13:43:10Z)
• Infi-Med: Low-Resource Medical MLLMs with Robust Reasoning Evaluation [33.22110638954145]
  We propose Infi-Med, a comprehensive framework for medical large language models (MLLMs)<n>Infi-Med introduces three key innovations: (1) a resource-efficient approach through curating and constructing high-quality supervised fine-tuning datasets with minimal sample requirements; (2) enhanced multimodal reasoning capabilities for cross-modal integration and clinical task understanding; and (3) a systematic evaluation system that assesses model performance across medical modalities and task types.<n>Our experiments demonstrate that Infi-Med achieves state-of-the-art (SOTA) performance in general medical reasoning while maintaining rapid adaptability to clinical scenarios.
  arXiv  Detail & Related papers  (2025-05-29T10:31:57Z)
• Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation [0.0]
  Large language models (LLMs) have shown impressive capabilities in natural language processing tasks, including dialogue generation.<n>This research aims to conduct a novel comparative analysis of two prominent techniques, fine-tuning with LoRA and the Retrieval-Augmented Generation framework.
  arXiv  Detail & Related papers  (2025-02-04T11:50:40Z)
• Medchain: Bridging the Gap Between LLM Agents and Clinical Practice through Interactive Sequential Benchmarking [58.25862290294702]
  We present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow.<n>We also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses.
  arXiv  Detail & Related papers  (2024-12-02T15:25:02Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• End-to-End Breast Cancer Radiotherapy Planning via LMMs with Consistency Embedding [47.360760580820966]
  We present RO-LMM, a comprehensive large multimodal model (LMM) tailored for the field of radiation oncology.<n>This model effectively manages a series of tasks within the clinical workflow, including clinical context summarization, radiation treatment plan suggestion, and plan-guided target volume segmentation.<n>We present a novel Consistency Embedding Fine-Tuning (CEFTune) technique, which boosts LMM's robustness to noisy inputs while preserving the consistency of handling clean inputs.
  arXiv  Detail & Related papers  (2023-11-27T14:49:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.