Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining

Abstract

Ranking consistently emerges as a primary focus in information retrieval research. Retrieval and ranking models serve as the foundation for numerous applications, including web search, open domain QA, enterprise domain QA, and text-based recommender systems. Typically, these models undergo training on triplets consisting of binary relevance assignments, comprising one positive and one negative passage. However, their utilization involves a context where a significantly more nuanced understanding of relevance is necessary, especially when re-ranking a large pool of potentially relevant passages. Although collecting positive examples through user feedback like impressions or clicks is straightforward, identifying suitable negative pairs from a vast pool of possibly millions or even billions of documents possess a greater challenge. Generating a substantial number of negative pairs is often necessary to maintain the high quality of the model. Several approaches have been suggested in lite

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymeghwani2024enhancing

Related papers

• Nv-retriever: Improving Text Embedding Models With Effective Hard-negative Mining (2024)0.00
• Optimizing Dense Retrieval Model Training With Hard Negatives (2021)16.34
• Docrerank: Single-page Hard Negative Query Generation For Training Multi-modal RAG Rerankers (2025)3.58
• Bica: Effective Biomedical Dense Retrieval With Citation-aware Hard Negatives (2025)0.00
• Towards Robust Ranker For Text Retrieval (2022)5.84
• Hard Negatives, Hard Lessons: Revisiting Training Data Quality For Robust Information Retrieval With Llms (2025)2.26
• Optimizing Legal Document Retrieval In Vietnamese With Semi-hard Negative Mining (2025)0.00
• Few-shot Prompting For Pairwise Ranking: An Effective Non-parametric Retrieval Model (2024)5.84