Gemex: A Large-scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis

Authors: B Liu, K Zou, LM Zhan, Z Lu, X Dong, Y Chen, C Xie, J Cao, XM Wu, H Fu
Time: 2025
Journal: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)

Abstract

We present Gemex, a large-scale medical Visual Question Answering (VQA) benchmark specifically designed for chest X-ray diagnosis. Gemex provides groundable and explainable answers, addressing the need for interpretable AI in medical imaging.

Keywords: medical VQA, chest X-ray, explainable AI, medical imaging

Citation

B Liu, K Zou, LM Zhan, Z Lu, X Dong, Y Chen, C Xie, J Cao, XM Wu, H Fu, "Gemex: A Large-scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis," Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025.