# Biomedical Visual Instruction Tuning with Clinician Preference Alignment

arXiv: https://arxiv.org/abs/2406.13173 · HTML: https://mlsanity.com/paper/2406.13173/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 40 of its 50 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

## Builds on (most cited first, 30 of 40)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [Towards Generalist Biomedical AI](https://mlsanity.com/paper/2307.14334/) (2023)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [Text Classification via Large Language Models](https://mlsanity.com/paper/2305.08377/) (2023)
- [Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training](https://mlsanity.com/paper/2209.07098/) (2022)
- [GPT-RE: In-context Learning for Relation Extraction using Large Language Models](https://mlsanity.com/paper/2305.02105/) (2023)

## Built on by (most cited first, 21 of 21)

- [Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback](https://mlsanity.com/paper/2501.01377/) (2025)
- [QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training](https://mlsanity.com/paper/2506.00711/) (2025)
- [TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records](https://mlsanity.com/paper/2503.04176/) (2025)
- [CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models](https://mlsanity.com/paper/2503.07667/) (2025)
- [SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis](https://mlsanity.com/paper/2506.02096/) (2025)
- [Uncertainty-Aware Large Language Models for Explainable Disease Diagnosis](https://mlsanity.com/paper/2505.03467/) (2025)
- [Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal Learning](https://mlsanity.com/paper/2505.17436/) (2025)
- [From large language models to multimodal AI: A scoping review on the potential of generative AI in medicine](https://mlsanity.com/paper/2502.09242/) (2025)
- [CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale](https://mlsanity.com/paper/2507.06959/) (2025)
- [Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation](https://mlsanity.com/paper/2512.16201/) (2025)
- [Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models](https://mlsanity.com/paper/2507.09209/) (2025)
- [MedBLINK: Probing Basic Perception in Multimodal Language Models for Medicine](https://mlsanity.com/paper/2508.02951/) (2025)
- [AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering](https://mlsanity.com/paper/2510.02328/) (2025)
- [Visual Instruction-Finetuned Language Model for Versatile Brain MR Image Tasks](https://mlsanity.com/paper/2604.02748/) (2026)
- [MGH Radiology Llama: A Llama 3 70B Model for Radiology](https://mlsanity.com/paper/2408.11848/) (2024)
- [EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning](https://mlsanity.com/paper/2510.19893/) (2025)
- [Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models](https://mlsanity.com/paper/2604.09841/) (2026)
- [StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning](https://mlsanity.com/paper/2607.00465/) (2026)
- [Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language Models](https://mlsanity.com/paper/2607.13860/) (2026)
- [Multi-LLM Collaborative MRI Report Generation for Visual Instruction Tuning in Brain Oncology](https://mlsanity.com/paper/2607.14581/) (2026)
- [DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning](https://mlsanity.com/paper/2608.09907/) (2026)

## Abstract (arXiv)

Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains like biomedicine requires large-scale domain-specific instruction datasets. While existing works have explored curating such datasets automatically, the resultant datasets are not explicitly aligned with domain expertise. In this work, we propose a data-centric framework, Biomedical Visual Instruction Tuning with Clinician Preference Alignment (BioMed-VITAL), that incorporates clinician preferences into both stages of generating and selecting instruction data for tuning biomedical multimodal foundation models. First, during the generation stage, we prompt the GPT-4V generator with a diverse set of clinician-selected demonstrations for preference-aligned data candidate generation. Then, during the selection phase, we train a separate selection model, which explicitly distills clinician and policy-guided model preferences into a rating function to select high-quality data for medical instruction tuning. Results show that the model tuned with the instruction-following data from our method demonstrates a significant improvement in open visual chat (18.5% relatively) and medical VQA (win rate up to 81.73%). Our instruction-following data and models are available at BioMed-VITAL.github.io.