# Effectively Fine-tune to Improve Large Multimodal Models for Radiology Report Generation

arXiv: https://arxiv.org/abs/2312.01504 · HTML: https://mlsanity.com/paper/2312.01504/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 3 Dec 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Generating Radiology Reports via Memory-driven Transformer](https://mlsanity.com/paper/2010.16056/) (2020)
- [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)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [Clinically Accurate Chest X-Ray Report Generation](https://mlsanity.com/paper/1904.02633/) (2019)
- [From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models](https://mlsanity.com/paper/2212.10846/) (2022)
- [Improving Chest X-Ray Report Generation by Leveraging Warm Starting](https://mlsanity.com/paper/2201.09405/) (2022)
- [Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards](https://mlsanity.com/paper/2210.12186/) (2022)
- [Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models](https://mlsanity.com/paper/2303.05977/) (2023)
- [Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors](https://mlsanity.com/paper/2210.06340/) (2022)
- [Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning](https://mlsanity.com/paper/2302.04732/) (2023)

## Built on by (most cited first, 3 of 3)

- [Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation](https://mlsanity.com/paper/2405.09586/) (2024)
- [A Multimodal Multi-Agent Framework for Radiology Report Generation](https://mlsanity.com/paper/2505.09787/) (2025)
- [Opportunities and challenges in the application of large artificial intelligence models in radiology](https://mlsanity.com/paper/2403.16112/) (2024)

## Abstract (arXiv)

Writing radiology reports from medical images requires a high level of domain expertise. It is time-consuming even for trained radiologists and can be error-prone for inexperienced radiologists. It would be appealing to automate this task by leveraging generative AI, which has shown drastic progress in vision and language understanding. In particular, Large Language Models (LLM) have demonstrated impressive capabilities recently and continued to set new state-of-the-art performance on almost all natural language tasks. While many have proposed architectures to combine vision models with LLMs for multimodal tasks, few have explored practical fine-tuning strategies. In this work, we proposed a simple yet effective two-stage fine-tuning protocol to align visual features to LLM's text embedding space as soft visual prompts. Our framework with OpenLLaMA-7B achieved state-of-the-art level performance without domain-specific pretraining. Moreover, we provide detailed analyses of soft visual prompts and attention mechanisms, shedding light on future research directions.