# Cascaded Retrieval with Cross-Modal Query Refinement for Efficient Visual Document Search

arXiv: https://arxiv.org/abs/2610.20367 · HTML: https://mlsanity.com/paper/2610.20367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 24 of 24)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [VisualMRC: Machine Reading Comprehension on Document Images](https://mlsanity.com/paper/2101.11272/) (2021)
- [PLAID: An Efficient Engine for Late Interaction Retrieval](https://mlsanity.com/paper/2205.09707/) (2022)
- [jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval](https://mlsanity.com/paper/2506.18902/) (2025)
- [ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents](https://mlsanity.com/paper/2502.18017/) (2025)
- [VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents](https://mlsanity.com/paper/2504.09795/) (2025)
- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback](https://mlsanity.com/paper/2108.13454/) (2021)
- [REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark](https://mlsanity.com/paper/2502.12342/) (2025)
- [Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach](https://mlsanity.com/paper/2010.01195/) (2020)
- [Rethinking the Role of Token Retrieval in Multi-Vector Retrieval](https://mlsanity.com/paper/2304.01982/) (2023)
- [Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model](https://mlsanity.com/paper/2507.05513/) (2025)
- [Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations](https://mlsanity.com/paper/2404.18812/) (2024)
- [Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization](https://mlsanity.com/paper/2510.05038/) (2025)
- [Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval](https://mlsanity.com/paper/2505.05666/) (2025)
- [Optimizing Test-Time Query Representations for Dense Retrieval](https://mlsanity.com/paper/2205.12680/) (2022)

## Abstract (arXiv)

Retrieving information from visually rich documents requires matching queries against pages that contain complex evidence in tables, figures, and layout-dependent structures. Current vision-language retrievers address this but incur query-time costs that grow with corpus size and are impractical to scale. We propose SCOUT, a cascaded two-track retrieval framework that separates retrieval performance from exhaustive search. The visual track first uses a lightweight parent retriever to filter the corpus to a compact candidate pool, then applies a stronger multi-vector reranker only to those candidates. In parallel, a semantic track retrieves over hierarchical page and document summaries generated offline to provide a signal complementary to visual matching. The outputs are fused through cross-modal query refinement, which uses semantic scores to adjust the visual query representation before final ranking. We evaluate SCOUT on 4 major benchmarks against 6 baselines and observe a significant query-time latency improvement up to 80.7x (28.8x on average) relative to the best baseline, while exceeding state-of-the-art retrieval performance by up to 7.8% NDCG across all benchmarks.