mlsanityData to 14 Oct 2026

Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models

arXiv 2507.09209 ↗First posted 12 Jul 2025cs.CVcited by 4

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

The rapid advancements in Vision Language Models (VLMs) have prompted the development of multi-modal medical assistant systems. Despite this progress, current models still have inherent probabilistic uncertainties, often producing erroneous or unverified responses-an issue with serious implications in medical applications. Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning. However, these training-dependent strategies are costly and still lack sufficient alignment with clinical expertise. To address these issues, we propose an expert-in-the-loop framework named Expert-Controlled Classifier-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training. This framework introduces an uncertainty estimation strategy to identify unreliable outputs. It then retrieves relevant references to assist experts in highlighting key terms and applies classifier-free guidance to refine the token embeddings of MedVLM, ensuring that the adjusted outputs are correct and align with expert highlights. Evaluations across three medical visual question answering benchmarks demonstrate that the proposed Expert-CFG, with 4.2B parameters and limited expert annotations, outperforms state-of-the-art models with 13B parameters. The results demonstrate the feasibility of deploying such a system in resource-limited settings for clinical use.

Key facts. Cited by 4 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 49 of its 60 references that are in the map. First posted on arXiv 12 Jul 2025.

Builds on

49 of 60 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models16 Oct
  2. 2024Cost-effective Instruction Learning for Pathology Vision and Language Analysis25 Jul
  3. 2024RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models6 Jul
  4. 2024HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale27 Jun
  5. 2024Advancing High Resolution Vision-Language Models in Biomedicine12 Jun
  6. 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models10 Jun
  7. 2024Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models16 Apr
  8. 2024M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models31 Mar
  9. 2024MultiMedEval: A Benchmark and a Toolkit for Evaluating Medical Vision-Language Models14 Feb
  10. 2024PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging5 Jan
  11. 2023Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V29 Oct
  12. 2023OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and Dialogue21 Jun
3 more
  1. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun
  2. 2023BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks26 May
  3. 2022Self-supervised vision-language pretraining for Medical visual question answering24 Nov

Other references · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  7. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  8. 2017Billion-scale similarity search with GPUscited by 2,497
  9. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  10. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  11. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  12. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 688
22 more
  1. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 547
  2. 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 538
  3. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 478
  4. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  5. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 449
  6. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 392
  7. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 357
  8. 2023PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answeringcited by 338
  9. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Modelscited by 316
  10. 2023Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Datacited by 179
  11. 2023Stay on topic with Classifier-Free Guidancecited by 91
  12. 2023Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videoscited by 86
  13. 2023Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Modelscited by 80
  14. 2023CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuningcited by 69
  15. 2023Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Modelscited by 58
  16. 2024CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Datasetcited by 35
  17. 2023RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-trainingcited by 31
  18. 2024Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicinecited by 31
  19. 2023Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answeringcited by 29
  20. 2023Prompt Highlighter: Interactive Control for Multi-Modal LLMscited by 29
  21. 2024Biomedical Visual Instruction Tuning with Clinician Preference Alignmentcited by 21
  22. 2024PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understandingcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuningcited by 2
  2. 2026MedProbCLIP: Probabilistic Adaptation of Vision-Language Foundation Model for Reliable Radiograph-Report Retrievalcited by 1
  3. 2025Improving Few-Shot Change Detection Visual Question Answering via Decision-Ambiguity-guided Reinforcement Fine-Tuningcited by 0
  4. 2026Counterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks
  2. 2024Fusion of Domain-Adapted Vision and Language Models for Medical Visual Question Answering
  3. 2025Benchmarking and Mitigating Sycophancy in Medical Vision Language Models
  4. 2026To Agree or To Be Right? The Grounding-Sycophancy Tradeoff in Medical Vision-Language Models
  5. 2026Sparse Spectral LoRA: Routed Experts for Medical VLMs
  6. 2025How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study
  7. 2026Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following
  8. 2026Benchmarking Direct Preference Optimization for Medical Large Vision-Language Models