# CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation

arXiv: https://arxiv.org/abs/2604.18967 · HTML: https://mlsanity.com/paper/2604.18967/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 63 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [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)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation](https://mlsanity.com/paper/2010.10042/) (2020)
- [Clinically Accurate Chest X-Ray Report Generation](https://mlsanity.com/paper/1904.02633/) (2019)
- [Exploring scalable medical image encoders beyond text supervision](https://mlsanity.com/paper/2401.10815/) (2024)
- [GREEN: Generative Radiology Report Evaluation and Error Notation](https://mlsanity.com/paper/2405.03595/) (2024)
- [The Devil in Linear Transformer](https://mlsanity.com/paper/2210.10340/) (2022)
- [Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards](https://mlsanity.com/paper/2210.12186/) (2022)
- [RaTEScore: A Metric for Radiology Report Generation](https://mlsanity.com/paper/2406.16845/) (2024)
- [Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation](https://mlsanity.com/paper/2502.20056/) (2025)
- [Libra: Leveraging Temporal Images for Biomedical Radiology Analysis](https://mlsanity.com/paper/2411.19378/) (2024)
- [RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation](https://mlsanity.com/paper/2306.07206/) (2023)
- [Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation](https://mlsanity.com/paper/2307.09758/) (2023)
- [RadEval: A framework for radiology text evaluation](https://mlsanity.com/paper/2509.18030/) (2025)
- [Automated Structured Radiology Report Generation](https://mlsanity.com/paper/2505.24223/) (2025)
- [DeltaNet:Conditional Medical Report Generation for COVID-19 Diagnosis](https://mlsanity.com/paper/2211.13229/) (2022)
- [Pragmatic Radiology Report Generation](https://mlsanity.com/paper/2311.17154/) (2023)
- [e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation](https://mlsanity.com/paper/2408.03500/) (2024)
- [PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report Generation](https://mlsanity.com/paper/2508.05353/) (2025)
- [The Impact of Auxiliary Patient Data on Automated Chest X-Ray Report Generation and How to Incorporate It](https://mlsanity.com/paper/2406.13181/) (2024)
- [Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.03906/) (2025)

## Abstract (arXiv)

Chest X-ray (CXR) radiology report generation (RRG) models have shown rapid progress on automated metrics, yet their clinical utility remains uncertain due to limited qualitative evaluation by radiologists. We present CXRMate-2, a state-of-the-art CXR RRG model that enables tractable reinforcement learning (RL) through structured multimodal temporal embeddings and high-resolution visual feature compression, for efficient, unified conditioning of an LLM decoder on visual, textual, and temporal context from a study and its prior. This enables group relative policy optimisation (GRPO), where a proposed reward function is used to improve semantic alignment with radiologist reports. Across the MIMIC-CXR, CheXpert Plus, and ReXgradient datasets, CXRMate-2 achieves statistically significant improvements over strong benchmarks, including gains of 11.2% and 24.4% in GREEN and RadGraph-XL, respectively, on MIMIC-CXR relative to MedGemma 1.5 (4B). To directly compare CXRMate-2 against radiologist reporting, we conduct a blinded, randomised qualitative retrospective evaluation. Three consultant radiologists compare generated and radiologist reports across 120 studies from the MIMIC-CXR test set. Generated reports were deemed acceptable (defined as preferred or rated equally to radiologist reports) in 45% of ratings, with no statistically significant difference in preference rates for seven of the eight analysed findings. Preferences for radiologist reports were driven primarily by higher recall, while generated reports were consistently preferred for readability. Together, these results define a clear pathway to clinically acceptable CXR RRG. Improving recall and the detection of subtle findings represents the primary remaining barrier to non-inferiority with radiologist reporting, positioning CXR RRG for prospective evaluation in assistive, radiologist-led workflows.