@inproceedings{huang-etal-2025-pathohr,
    title = "{P}atho{HR}: Hierarchical Reasoning for Vision-Language Models in Pathology",
    author = "Huang, Yating  and
      Huang, Ziyan  and
      Xiang, Lintao  and
      Yang, Qijun  and
      Yin, Hujun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.124/",
    doi = "10.18653/v1/2025.findings-emnlp.124",
    pages = "2296--2311",
    ISBN = "979-8-89176-335-7",
    abstract = "Accurate analysis of pathological images is essential for automated tumor diagnosis but remains challenging due to high structural similarity and subtle morphological variations in tissue images. Current vision-language (VL) models often struggle to capture the complex reasoning required for interpreting structured pathological reports. To address these limitations, we propose PathoHR-Bench, a novel benchmark designed to evaluate VL models' abilities in hierarchical semantic understanding and compositional reasoning within the pathology domain. Results of this benchmark reveal that existing VL models fail to effectively model intricate cross-modal relationships, hence limiting their applicability in clinical setting. To overcome this, we further introduce a pathology-specific VL training scheme that generates enhanced and perturbed samples for multimodal contrastive learning. Experimental evaluations demonstrate that our approach achieves state-of-the-art performance on PathoHR-Bench and six additional pathology datasets, highlighting its effectiveness in fine-grained pathology representation."
}