# From Compound Figures to Composite Understanding: Developing a Multi-Modal LLM from Biomedical Literature with Medical Multiple-Image Benchmarking and Validation

arXiv: https://arxiv.org/abs/2511.22232 · HTML: https://mlsanity.com/paper/2511.22232/

## Key facts

- Cited by 2 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 12 of its 160 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Placed in

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

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

- [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)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [ELIXR: Towards a general purpose X-ray artificial intelligence system through alignment of large language models and radiology vision encoders](https://mlsanity.com/paper/2308.01317/) (2023)
- [Multimodal Large Language Models for Medicine: A Comprehensive Survey](https://mlsanity.com/paper/2504.21051/) (2025)
- [Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights](https://mlsanity.com/paper/2511.06738/) (2025)

## Built on by (most cited first, 2 of 2)

- [VOLMO: Versatile and Open Large Models for Ophthalmology](https://mlsanity.com/paper/2603.23953/) (2026)
- [MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models](https://mlsanity.com/paper/2607.07673/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) are increasingly capable in medical imaging, yet most focus on single-image settings. Clinical interpretation often requires integrating evidence across multiple images, such as different modalities, views, or time points. However, large-scale medical multi-image data and training strategies for such reasoning remain limited. We construct PMC-MI, a large-scale resource comprising 234,956 instruction instances derived from biomedical compound figures, with 10,555 multi-subimage instances structured for reinforcement learning and assessed by medical reviewers. We also introduce PMC-MI-Bench, a manually reviewed benchmark separated at the source-article level. We further propose a three-stage training framework, instantiated as M3LLM, combining supervised fine-tuning on multi-image instructions, selection-aware reinforcement learning for question-conditioned visual-evidence selection, and supervised consolidation on a broader instruction mixture. Evaluating M3LLM on PMC-MI-Bench, two public medical benchmarks, longitudinal chest radiographs, and a retrospective dermatology cohort reveals it achieves the highest performance among representative MLLMs. On PMC-MI-Bench, M3LLM scored 81.6, 84.6, and 85.2 on single-subimage, multi-subimage, and relative-position tasks, respectively, outperforming the strongest baselines (75.6, 79.1, and 77.6). It also set new records on the provenance-screened OmniMedVQA (88.6%) and MMMU-Med (68.0%), alongside top performance in two clinical settings after task-specific adaptation. These findings support using literature-derived multi-image supervision and targeted post-training for medical multi-image MLLMs. Data and code are publicly available.