Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lan, Mengfei, Zheng, Lecheng, Kilicoglu, Halil
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.15591
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917415785332736
author Lan, Mengfei
Zheng, Lecheng
Kilicoglu, Halil
author_facet Lan, Mengfei
Zheng, Lecheng
Kilicoglu, Halil
contents Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedical generative retrievers build 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15591
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels
Lan, Mengfei
Zheng, Lecheng
Kilicoglu, Halil
Information Retrieval
Artificial Intelligence
Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedical generative retrievers build 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.
title BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2604.15591