REVIEW 10 cited by
OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in various multimodal tasks. However, their potential in the medical domain remains largely unexplored. A significant challenge arises from the scarcity of diverse medical images spanning various modalities and anatomical regions, which is essential in real-world medical applications. To solve this problem, in this paper, we introduce OmniMedVQA, a novel comprehensive medical Visual Question Answering (VQA) benchmark. This benchmark is collected from 73 different medical datasets, including 12 different modalities and covering more than 20 distinct anatomical regions. Importantly, all images in this benchmark are sourced from authentic medical scenarios, ensuring alignment with the requirements of the medical field and suitability for evaluating LVLMs. Through our extensive experiments, we have found that existing LVLMs struggle to address these medical VQA problems effectively. Moreover, what surprises us is that medical-specialized LVLMs even exhibit inferior performance to those general-domain models, calling for a more versatile and robust LVLM in the biomedical field. The evaluation results not only reveal the current limitations of LVLM in understanding real medical images but also highlight our dataset's significance. Our code with dataset are available at https://github.com/OpenGVLab/Multi-Modality-Arena.
Forward citations
Cited by 10 Pith papers
-
MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models
Introduces MMBU benchmark for VLMs in biomedicine and demonstrates that established benchmarks mask perception deficiencies in evaluated models.
-
Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks
Neural-MedBench reveals sharp performance drops in state-of-the-art VLMs on reasoning-intensive neurology tasks compared to conventional classification benchmarks, with reasoning failures dominating errors.
-
MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation
A real multimodal Chinese online-consultation benchmark of 5,620 cases finds frontier LLMs below physicians, with safety-sensitive error avoidance as the main gap.
-
CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series
CLIR-Bench shows generalist and time-series LLMs struggle to ground clinical answers in sparse irregular ICU evidence, with top accuracy near 50% and weak causal evidence use.
-
MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation
On a new benchmark of 5,620 real multimodal online consultations, top LLMs trail the original physicians mainly because they trigger more unsafe or unsupported negative criteria.
-
Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA
A composite loss with Brier calibration, anchor regularization, contrastive alignment from 2x2 perturbations, and KL stabilization reduces calibration error by over 60% in medical VQA while preserving accuracy.
-
RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity
RA-QA converts 11 public respiratory-audio datasets into 9M template-generated QA pairs and shows current audio-language models score near zero on clinical task accuracy.
-
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.
-
Objective-Aligned Direct Answer SFT for Robust Multi-Frame Medical VQA
Direct answer-only supervised fine-tuning is the most robust adaptation family on MedFrameQA, beating frozen baselines by ~6 points and outperforming complex variants on seed stability.
-
Inference-Time Agentic Decision Rules Beat Longer Evolving Search for Multi-Image Medical Reasoning
On MedFrameQA, order-vote (57.89%) beats fixed prompting (52.73%) and order-rerank (55.79%), and a single 100-generation run drops final-test accuracy to 56.02%.
Discussion (0). Sign in to comment.