@inproceedings{lan-etal-2026-biohicl,
    title = "{B}io{H}i{CL}: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with {M}e{SH} Labels",
    author = "Lan, Mengfei  and
      Zheng, Lecheng  and
      Kilicoglu, Halil",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-short.62/",
    pages = "759--769",
    ISBN = "979-8-89176-391-3",
    abstract = "Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedical generative retrievers built on coarse binary relevance signals, limiting their ability to capture semantic overlap. We propose BioHiCL - Biomedical Retrieval with Hierarchical Multi-Label Contrastive Learning, which leverages hierarchical MeSH annotations to provide structured supervision for multi-label contrastive learning. Our models, BioHiCL-Base (0.1B) and BioHiCL-Large (0.3B), achieve promising performance on biomedical retrieval, sentence similarity, and question answering tasks, while remaining computationally efficient for deployment."
}