mlsanityData to 14 Oct 2026

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

arXiv 2607.18988 ↗First posted 21 Jul 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

also in 1 more
Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 19 of its 30 references that are in the map. First posted on arXiv 21 Jul 2026.

Builds on

19 of 30 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Radiology's Last Exam (RadLE): Benchmarking Frontier Multimodal AI Against Human Experts and a Taxonomy of Visual Reasoning Errors in Radiology29 Sep
  2. 2024Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review4 Mar
  3. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun

Other references · 16

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  6. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
  7. 2023OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Modelscited by 565
  8. 2025MedGemma Technical Reportcited by 436
  9. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 319
  10. 2024Capabilities of Gemini Models in Medicinecited by 237
  11. 2022Cross-modal Memory Networks for Radiology Report Generationcited by 185
  12. 2021Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generationcited by 162
4 more
  1. 2020Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generationcited by 141
  2. 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 140
  3. 2019Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generationcited by 102
  4. 2025MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback
  2. 2026CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
  3. 2026Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
  4. 2026CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation
  5. 2026Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning
  6. 2023Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation
  7. 2025RadHiera: Semantic Hierarchical Reinforcement Learning for Medical Report Generation
  8. 2026SDR: Set-Distance Rewards for Radiology Report Generation