DobicVLM: Aligning Chest X-Ray Report Generation with Clinically-Grounded Programmatic Rewards via Group Relative Policy Optimization

• URL: http://arxiv.org/abs/2607.18988v2
• Date: Sat, 25 Jul 2026 10:38:52 GMT
• Title: DobicVLM: Aligning Chest X-Ray Report Generation with Clinically-Grounded Programmatic Rewards via Group Relative Policy Optimization
• Abstract summary: We introduce DobicVLM, a vision-language model combining supervised fine-tuning on MedGemma-4B with Group Relative Policy Optimization.<n>Our approach uses interpretable, rule-based reward components; structural verification, anatomical checklist, semantic similarity, and length constraints.<n>DobicVLM outperforms Gemini 2.5 Flash across the majority of criteria, achieving the highest impression accuracy (27.2%) and medical terminology (86.5%) compared to both Gemini 2.5 Flash and MedGemma 4B baselines.
• Score: 0.4418222884390162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical imaging is a cornerstone of diagnostics, yet automated chest X-ray report generation struggles with structural adherence, anatomical completeness, and semantic faithfulness. We introduce DobicVLM, a vision-language model combining supervised fine-tuning on MedGemma-4B with Group Relative Policy Optimization (GRPO) and clinically-grounded programmatic rewards. Our approach uses interpretable, rule-based reward components; structural verification, anatomical checklist, semantic similarity, and length constraints to enforce clinical standards without neural reward models. Trained on 1,000 de-identified image-report pairs from a private clinical dataset (with ethics approval and compliance to local regulations), DobicVLM is evaluated via blinded expert review on 69 held-out cases. DobicVLM outperforms Gemini 2.5 Flash across the majority of criteria, achieving the highest impression accuracy (27.2%) and medical terminology (86.5%) compared to both Gemini 2.5 Flash and MedGemma 4B baselines, with minor trade-offs in completeness and referrals. This demonstrates GRPO's value for transparent alignment in resource-limited settings. Keywords: Vision-Language Models, Radiology Report Generation, Reinforcement Learning, Medical AI, GRPO

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding [67.57715989349471]
  Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge.<n>We introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding.<n>We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks.
  arXiv  Detail & Related papers  (2026-07-27T17:59:49Z)
• Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs [53.697403481143404]
  Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks.<n>But they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback.
  arXiv  Detail & Related papers  (2026-06-10T18:35:36Z)
• MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models [83.50100003741628]
  Vision and language models (VLMs) hold immense promise to transform biomedical imaging.<n>We introduce the Massive Multimodal Biomedical Understanding (MMBU) benchmark.<n>It is the largest vision and language benchmark to date, covering 35 submodalities with rich structured metadata.
  arXiv  Detail & Related papers  (2026-06-04T20:24:47Z)
• ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection [1.1273389819207937]
  We introduce ProMedical, a unified alignment framework grounded in fine-grained clinical criteria.<n>We first construct ProMedical-Preference-50k, a dataset generated via a human-in-the-loop pipeline.<n>Unlike traditional scalar reward models, our approach explicitly disentangles safety constraints from general proficiency.
  arXiv  Detail & Related papers  (2026-04-09T14:57:33Z)
• Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment [56.62016795093786]
  Cerebra is an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis.<n>It supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete.<n>Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation.
  arXiv  Detail & Related papers  (2026-03-23T05:46:45Z)
• VIVID-Med: LLM-Supervised Structured Pretraining for Deployable Medical ViTs [24.283989257873085]
  We introduce VIVID-Med, a novel framework that leverages a frozen large language model (LLM) as a structured semantic teacher to pretrain medical vision transformers (ViTs)<n> VIVID-Med translates clinical findings into verifiable field-state pairs via a Unified MedicalNIST (UMS), utilizing answerability-aware masking to focus optimization.<n>It achieves a macro-AUC of 0.8588, outperforming BiomedCLIP by +6.65 points while using 500x less data.
  arXiv  Detail & Related papers  (2026-03-10T02:42:51Z)
• VL-OrdinalFormer: Vision Language Guided Ordinal Transformers for Interpretable Knee Osteoarthritis Grading [6.106307107513728]
  VLOrdinalFormer is a vision language guided ordinal learning framework for automated KOA grading from knee radiographs.<n>The proposed method combines a ViT L16 backbone with CORAL based ordinal regression and a Contrastive Language Image Pretraining (CLIP) driven semantic alignment module.<n>Experiments conducted on the publicly available OAI kneeKL224 dataset demonstrate that VLOrdinalFormer achieves state of the art performance.
  arXiv  Detail & Related papers  (2025-12-31T03:01:31Z)
• Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation [25.148217482604746]
  We propose VALOR:Visual Alignment of Medical Vision-Language Models for Radiology Report Generation.<n>Our method introduces a reinforcement learning-based post-alignment framework utilizing Group-Relative Proximal Optimization (GRPO)<n>Experiments on multiple benchmarks demonstrate that VALOR substantially improves factual accuracy and visual grounding, achieving significant performance gains over state-of-the-art report generation methods.
  arXiv  Detail & Related papers  (2025-12-18T05:48:21Z)
• MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding [47.843626983298726]
  We introduce textbfMedVidBench, a large-scale benchmark of 531,850 video-instruction pairs across 8 medical sources spanning video, segment, and frame-level tasks.<n>While supervised fine-tuning on MedVidBench yields noticeable gains, standard Reinforcement Learning fails due to imbalanced reward scales across datasets.<n>We introduce textbfMedGRPO, a novel RL framework for balanced multi-dataset training with two key innovations.
  arXiv  Detail & Related papers  (2025-12-06T22:27:59Z)
• XBench: A Comprehensive Benchmark for Visual-Language Explanations in Chest Radiography [6.447908430647854]
  We present the first systematic benchmark for evaluating cross-modal interpretability in chest X-rays.<n>We generate visual explanations using cross-attention and similarity-based localization maps.<n>We quantitatively assess their alignment with radiologist-annotated regions across multiple pathologies.
  arXiv  Detail & Related papers  (2025-10-22T13:52:19Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)

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.