Docrerank: Single-page Hard Negative Query Generation For Training Multi-modal RAG Rerankers

Abstract

Rerankers play a critical role in multimodal Retrieval-Augmented Generation (RAG) by refining ranking of an initial set of retrieved documents. Rerankers are typically trained using hard negative mining, whose goal is to select pages for each query which rank high, but are actually irrelevant. However, this selection process is typically passive and restricted to what the retriever can find in the available corpus, leading to several inherent limitations. These include: limited diversity, negative examples which are often not hard enough, low controllability, and frequent false negatives which harm training. Our paper proposes an alternative approach: Single-Page Hard Negative Query Generation, which goes the other way around. Instead of retrieving negative pages per query, we generate hard negative queries per page. Using an automated LLM-VLM pipeline, and given a page and its positive query, we create hard negatives by rephrasing the query to be as similar as possible in form and con

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keywasserman2025docrerank

Related papers

• Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining (2024)0.00
• Optimizing Dense Retrieval Model Training With Hard Negatives (2021)16.34
• Towards Robust Ranker For Text Retrieval (2022)5.84
• Syneg: Llm-driven Synthetic Hard-negatives For Dense Retrieval (2024)0.00
• Nv-retriever: Improving Text Embedding Models With Effective Hard-negative Mining (2024)0.00
• Hard Negatives, Hard Lessons: Revisiting Training Data Quality For Robust Information Retrieval With Llms (2025)2.26
• Bica: Effective Biomedical Dense Retrieval With Citation-aware Hard Negatives (2025)0.00
• RRRA: Resampling And Reranking Through A Retriever Adapter (2025)0.00