Bica: Effective Biomedical Dense Retrieval With Citation-aware Hard Negatives

Abstract

Hard negatives are essential for training effective retrieval models. Hard-negative mining typically relies on ranking documents using cross-encoders or static embedding models based on similarity metrics such as cosine distance. Hard negative mining becomes challenging for biomedical and scientific domains due to the difficulty in distinguishing between source and hard negative documents. However, referenced documents naturally share contextual relevance with the source document but are not duplicates, making them well-suited as hard negatives. In this work, we propose BiCA: Biomedical Dense Retrieval with Citation-Aware Hard Negatives, an approach for hard-negative mining by utilizing citation links in 20,000 PubMed articles for improving a domain-specific small dense retriever. We fine-tune the GTE_small and GTE_Base models using these citation-informed negatives and observe consistent improvements in zero-shot dense retrieval using nDCG@10 for both in-domain and out-of-domain tasks

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysinha2025bica

Related papers

• Nv-retriever: Improving Text Embedding Models With Effective Hard-negative Mining (2024)0.00
• Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining (2024)0.00
• ECI: Effective Contrastive Information To Evaluate Hard-negatives (2026)0.00
• Optimizing Dense Retrieval Model Training With Hard Negatives (2021)16.34
• VSE++: Improving Visual-semantic Embeddings With Hard Negatives (2017)0.00
• Hard Negatives, Hard Lessons: Revisiting Training Data Quality For Robust Information Retrieval With Llms (2025)2.26
• Syneg: Llm-driven Synthetic Hard-negatives For Dense Retrieval (2024)0.00
• Optimizing Legal Document Retrieval In Vietnamese With Semi-hard Negative Mining (2025)0.00