# Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation

arXiv: https://arxiv.org/abs/2608.08494 · HTML: https://mlsanity.com/paper/2608.08494/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [Generating Radiology Reports via Memory-driven Transformer](https://mlsanity.com/paper/2010.16056/) (2020)
- [CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://mlsanity.com/paper/2004.09167/) (2020)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model](https://mlsanity.com/paper/2311.13231/) (2023)
- [On the Automatic Generation of Medical Imaging Reports](https://mlsanity.com/paper/1711.08195/) (2017)
- [MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology](https://mlsanity.com/paper/2301.02228/) (2023)
- [When Radiology Report Generation Meets Knowledge Graph](https://mlsanity.com/paper/2002.08277/) (2020)
- [Interactive and Explainable Region-guided Radiology Report Generation](https://mlsanity.com/paper/2304.08295/) (2023)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation](https://mlsanity.com/paper/2303.10323/) (2023)
- [R2GenGPT: Radiology Report Generation with Frozen LLMs](https://mlsanity.com/paper/2309.09812/) (2023)
- [METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens](https://mlsanity.com/paper/2304.02211/) (2023)
- [PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation](https://mlsanity.com/paper/2308.12604/) (2023)
- [Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement](https://mlsanity.com/paper/2405.15973/) (2024)
- [Contrastive Attention for Automatic Chest X-ray Report Generation](https://mlsanity.com/paper/2106.06965/) (2021)
- [Knowledge Matters: Radiology Report Generation with General and Specific Knowledge](https://mlsanity.com/paper/2112.15009/) (2021)
- [RaTEScore: A Metric for Radiology Report Generation](https://mlsanity.com/paper/2406.16845/) (2024)
- [Automated Multi-level Preference for MLLMs](https://mlsanity.com/paper/2405.11165/) (2024)
- [Large Language Model with Region-guided Referring and Grounding for CT Report Generation](https://mlsanity.com/paper/2411.15539/) (2024)
- [STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering](https://mlsanity.com/paper/2406.19973/) (2024)
- [MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization](https://mlsanity.com/paper/2412.06141/) (2024)
- [Adaptive Preference Scaling for Reinforcement Learning with Human Feedback](https://mlsanity.com/paper/2406.02764/) (2024)
- [SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation](https://mlsanity.com/paper/2406.13532/) (2024)
- [RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection](https://mlsanity.com/paper/2505.14318/) (2025)

## Abstract (arXiv)

Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct Preference Optimization (DPO) has emerged as a promising post-training paradigm to enhance the performance of Supervised Fine-Tuned (SFT) MRG models, existing DPO-based MRG methods typically adopt a naive preference construction that directly pairs model-generated reports with ground truth reports. This strategy inadvertently entangles critical clinical findings with clinically irrelevant linguistic characteristics, and fundamentally lacks explicit vision-language alignment. To address these challenges, we propose DPO-Clin, a novel post-training framework that focuses preference optimization on clinical findings and cross-modal alignment. First, we introduce the Entity-level Clinical Diagnostic (ECD) module to perform a precise entity-level factual diagnosis. ECD guides the generation of linguistically-aligned report preference pairs, isolating clinical discrepancies from linguistic variations. Second, to achieve fine-grained cross-modal alignment, we develop M2DPO, a retrieval-augmented multi-modal DPO variant that enforces textual preference inversion triggered by visual context switches. Third, we locate correct yet highly uncertain predicted entities and apply counterfactual modifications to construct targeted preference data for latent risk mitigation, thereby further enhancing the model reliability. Extensive experiments on two public chest X-ray datasets (MIMIC-CXR and IU X-Ray) and an in-house endoscopy dataset demonstrate that DPO-Clin significantly improves the SFT baselines on clinical-aware metrics. Furthermore, it achieves superior performance over existing DPO-based MRG methods, exhibiting robust generalizability across distinct baseline architectures and diverse medical imaging modalities.