Search papers, labs, and topics across Lattice.
Tsinghua AISchool of Computer Science and Software EngineeringUniversity of NottinghamWenzhou Medical UniversityApr 22, 2026arXiv:2604.20350The paper introduces X-PCR, a new benchmark designed to evaluate the cross-modality progressive clinical reasoning capabilities of Multi-modal Large Language Models (MLLMs) in ophthalmic diagnosis. X-PCR features a six-stage progressive reasoning chain and a cross-modality reasoning task integrating six ophthalmic imaging modalities, using a dataset of 26,415 images and 177,868 VQA pairs. Experiments on 21 MLLMs demonstrate significant limitations in their ability to perform progressive reasoning and cross-modal integration within a clinical context.
MLLMs still struggle to integrate diverse data for clinical reasoning, as evidenced by their poor performance on a new ophthalmology benchmark spanning image quality assessment to diagnosis.
Despite significant progress in Multi-modal Large Language Models (MLLMs), their clinical reasoning capacity for multi-modal diagnosis remains largely unexamined. Current benchmarks, mostly single-modality data, can't evaluate progressive reasoning and cross-modal integration essential for clinical practice. We introduce the Cross-Modality Progressive Clinical Reasoning (X-PCR) benchmark, the first comprehensive evaluation of MLLMs through a complete ophthalmology diagnostic workflow, with two reasoning tasks: 1) a six-stage progressive reasoning chain spanning image quality assessment to clinical decision-making, and 2) a cross-modality reasoning task integrating six imaging modalities. The benchmark comprises 26,415 images and 177,868 expert-verified VQA pairs curated from 51 public datasets, covering 52 ophthalmic diseases. Evaluation of 21 MLLMs reveals critical gaps in progressive reasoning and cross-modal integration. Dataset and code: https://github.com/CVI-SZU/X-PCR.
