# LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts

arXiv: https://arxiv.org/abs/2412.12001 · HTML: https://mlsanity.com/paper/2412.12001/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 61 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [MIMIC-IT: Multi-Modal In-Context Instruction Tuning](https://mlsanity.com/paper/2306.05425/) (2023)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data](https://mlsanity.com/paper/2308.02463/) (2023)
- [Rho-1: Not All Tokens Are What You Need](https://mlsanity.com/paper/2404.07965/) (2024)
- [Exploring scalable medical image encoders beyond text supervision](https://mlsanity.com/paper/2401.10815/) (2024)
- [ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models](https://mlsanity.com/paper/2302.07257/) (2023)
- [A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation](https://mlsanity.com/paper/2401.12208/) (2024)
- [MAIRA-1: A specialised large multimodal model for radiology report generation](https://mlsanity.com/paper/2311.13668/) (2023)
- [Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation](https://mlsanity.com/paper/2109.12242/) (2021)
- [Automated Generation of Accurate & Fluent Medical X-ray Reports](https://mlsanity.com/paper/2108.12126/) (2021)
- [Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation](https://mlsanity.com/paper/2307.09758/) (2023)
- [Controllable Chest X-Ray Report Generation from Longitudinal Representations](https://mlsanity.com/paper/2310.05881/) (2023)
- [Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment](https://mlsanity.com/paper/2405.17871/) (2024)
- [Vision-Language Generative Model for View-Specific Chest X-ray Generation](https://mlsanity.com/paper/2302.12172/) (2023)
- [TiBiX: Leveraging Temporal Information for Bidirectional X-ray and Report Generation](https://mlsanity.com/paper/2403.13343/) (2024)

## Built on by (most cited first, 13 of 13)

- [PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report Generation](https://mlsanity.com/paper/2508.05353/) (2025)
- [A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluation](https://mlsanity.com/paper/2510.12444/) (2025)
- [CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation](https://mlsanity.com/paper/2604.10420/) (2026)
- [AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation](https://mlsanity.com/paper/2605.17071/) (2026)
- [CLARIFID: Improving Radiology Report Generation by Reinforcing Clinically Accurate Impressions and Enforcing Detailed Findings](https://mlsanity.com/paper/2507.17234/) (2025)
- [Standardizing Longitudinal Radiology Report Evaluation via Large Language Model Annotation](https://mlsanity.com/paper/2601.16753/) (2026)
- [Ran Score: a LLM-based Evaluation Score for Radiology Report Generation](https://mlsanity.com/paper/2603.22935/) (2026)
- [From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks](https://mlsanity.com/paper/2604.27453/) (2026)
- [GRCD: Grounded Region Change Detection for Multi-Finding Chest X-Ray Pairs](https://mlsanity.com/paper/2607.02719/) (2026)
- [PDD-RRG: Posterior Diagnostic Decision for Study-level Radiology Report Generation](https://mlsanity.com/paper/2608.03055/) (2026)
- [PACER: Progressive Availability-Conditioned Evidence Routing for Radiology Report Generation under Incomplete Clinical Context](https://mlsanity.com/paper/2609.34487/) (2026)
- [EviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision](https://mlsanity.com/paper/2610.02375/) (2026)
- [CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation](https://mlsanity.com/paper/2610.13059/) (2026)

## Abstract (arXiv)

Drafting radiology reports is a complex task requiring flexibility, where radiologists tail content to available information and particular clinical demands. However, most current radiology report generation (RRG) models are constrained to a fixed task paradigm, such as predicting the full ``finding'' section from a single image, inherently involving a mismatch between inputs and outputs. The trained models lack the flexibility for diverse inputs and could generate harmful, input-agnostic hallucinations. To bridge the gap between current RRG models and the clinical demands in practice, we first develop a data generation pipeline to create a new MIMIC-RG4 dataset, which considers four common radiology report drafting scenarios and has perfectly corresponded input and output. Secondly, we propose a novel large language model (LLM) based RRG framework, namely LLM-RG4, which utilizes LLM's flexible instruction-following capabilities and extensive general knowledge. We further develop an adaptive token fusion module that offers flexibility to handle diverse scenarios with different input combinations, while minimizing the additional computational burden associated with increased input volumes. Besides, we propose a token-level loss weighting strategy to direct the model's attention towards positive and uncertain descriptions. Experimental results demonstrate that LLM-RG4 achieves state-of-the-art performance in both clinical efficiency and natural language generation on the MIMIC-RG4 and MIMIC-CXR datasets. We quantitatively demonstrate that our model has minimal input-agnostic hallucinations, whereas current open-source models commonly suffer from this problem.