# SLaVA-CXR: Small Language and Vision Assistant for Chest X-ray Report Automation

arXiv: https://arxiv.org/abs/2409.13321 · HTML: https://mlsanity.com/paper/2409.13321/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 12 of 12)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [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)
- [Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data](https://mlsanity.com/paper/2308.02463/) (2023)
- [Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation](https://mlsanity.com/paper/2106.06963/) (2021)
- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)
- [LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model](https://mlsanity.com/paper/2401.02330/) (2024)
- [A Survey of Large Language Models in Medicine: Progress, Application, and Challenge](https://mlsanity.com/paper/2311.05112/) (2023)
- [TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones](https://mlsanity.com/paper/2312.16862/) (2023)

## Built on by (most cited first, 7 of 7)

- [Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report Generation](https://mlsanity.com/paper/2505.22222/) (2025)
- [Graph-based LLM over Semi-Structured Population Data for Dynamic Policy Response](https://mlsanity.com/paper/2510.05196/) (2025)
- [RadEyeVideo: Enhancing general-domain Large Vision Language Model for chest X-ray analysis with video representations of eye gaze](https://mlsanity.com/paper/2507.09097/) (2025)
- [HARE: an entity and relation centric evaluation framework for histopathology reports](https://mlsanity.com/paper/2509.16326/) (2025)
- [Artificial Intelligence-driven Intelligent Wearable Systems: A full-stack Integration from Material Design to Personalized Interaction](https://mlsanity.com/paper/2511.13565/) (2025)
- [Cross-Source Supervision for Bone Infection Segmentation in Dual-Modality PET-CT](https://mlsanity.com/paper/2605.16373/) (2026)
- [RAG4Outcome: A Retrieval-Augmented Multimodal Framework for Prognostic Prediction in Chronic Osteomyelitis](https://mlsanity.com/paper/2605.22833/) (2026)

## Abstract (arXiv)

Inspired by the success of large language models (LLMs), there is growing research interest in developing LLMs in the medical domain to assist clinicians. However, for hospitals, using closed-source commercial LLMs involves privacy issues, and developing open-source public LLMs requires large-scale computational resources, which are usually limited, especially in resource-efficient regions and low-income countries. We propose an open-source Small Language and Vision Assistant (SLaVA-CXR) that can be used for Chest X-Ray report automation. To efficiently train a small assistant, we first propose the Re3Training method, which simulates the cognitive development of radiologists and optimizes the model in the Recognition, Reasoning, and Reporting training manner. Then, we introduce a data synthesis method, RADEX, which can generate a high-quality and diverse training corpus with privacy regulation compliance. The extensive experiments show that our SLaVA-CXR built on a 2.7B backbone not only outperforms but also achieves 6 times faster inference efficiency than previous state-of-the-art larger models.