Research
BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels
arXiv:2604.15591v1 Announce Type: cross Abstract: Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedic
arXiv:2604.15591v1 Announce Type: cross Abstract: 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.
Related
- Efficient Process Reward Modeling via Contrastive Mutual Information
- Bottleneck Tokens for Unified Multimodal Retrieval
- Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching
- CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
Source: arXiv cs.AI | 2026-04-20