ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment

• URL: http://arxiv.org/abs/2604.07419v1
• Date: Wed, 08 Apr 2026 14:47:27 GMT
• Title: ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment
• Abstract summary: Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections.<n>Existing methods often employ Vision-Language Models (VLMs) to encode queries and visual pages into a shared embedding space.<n>We propose Reasoning-Guided Alignment (ReAlign) to provide fine-grained visual document descriptions as supervision signals for training.
• Score: 28.897559367200376
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections. Existing methods often employ Vision-Language Models (VLMs) to encode queries and visual pages into a shared embedding space, which is then optimized via contrastive training. However, during visual document representation, localized evidence is usually scattered across complex document layouts, making it difficult for retrieval models to capture crucial cues for effective embedding learning. In this paper, we propose Reasoning-Guided Alignment (ReAlign), a method that enhances visual document retrieval by leveraging the reasoning capability of VLMs to provide fine-grained visual document descriptions as supervision signals for training. Specifically, ReAlign employs a superior VLM to identify query-related regions on a page and then generates a query-aware description grounding the cropped visual regions. The retriever is then trained using these region-focused descriptions to align the semantics between queries and visual documents by encouraging the document ranking distribution induced by the region-focused descriptions to match that induced by the original query. Experiments on diverse visually rich document retrieval benchmarks demonstrate that ReAlign consistently improves visual document retrieval performance on both in-domain and out-of-domain datasets, achieving up to 2% relative improvements. Moreover, the advantages of ReAlign generalize across different VLM backbones by guiding models to better focus their attention on critical visual cues for document representation. All code and datasets are available at https://github.com/NEUIR/ReAlign.

Related papers

• ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval [62.80735412748694]
  ConceptFormer is a latent concept representation learning framework for visual document retrieval.<n>It query-relevant evidence as continuous, query-conditioned latent concepts that explicitly bridge localized visual evidence and semantic relevance.<n>It achieves 16.7% and 22.1% relative improvements in average NDCG@10 over the strongest visual retrieval baseline and the strongest OCR-based text retrieval baseline, respectively.
  arXiv  Detail & Related papers  (2026-08-16T12:07:12Z)
• VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval [40.36520318905935]
  We propose VaRS-Doc, a visual document retrieval framework that diversifies document representations.<n>VaRS-Doc achieves state-of-the-art retrieval performance, offering a practical solution to the mismatch between query-agnostic document encoding and query-specific retrieval needs.
  arXiv  Detail & Related papers  (2026-08-02T12:55:57Z)
• Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA [71.42483000929614]
  Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.<n>We propose Doc-$V*$, an textbfOCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
  arXiv  Detail & Related papers  (2026-04-15T11:12:27Z)
• MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns [80.05126590825121]
  MonkeyOCR v1.5 is a unified vision-language framework that enhances both layout understanding and content recognition.<n>To address complex table structures, we propose a visual consistency-based reinforcement learning scheme.<n>Two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables.
  arXiv  Detail & Related papers  (2025-11-13T15:12:17Z)
• RegionRAG: Region-level Retrieval-Augumented Generation for Visually-Rich Documents [40.107303323097646]
  modelname is a novel framework that shifts the retrieval paradigm from the document level to the region level.<n> Experiments on six benchmarks demonstrate that RegionRAG achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-10-31T08:00:32Z)
• VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents [30.012487475552575]
  We introduce a new RAG framework, VDocRAG, which can directly understand varied documents and modalities in a unified image format.<n>We also introduce OpenDocVQA, the first unified collection of open-domain document visual question answering datasets.
  arXiv  Detail & Related papers  (2025-04-14T01:50:33Z)
• QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding [53.69841526266547]
  Fine-tuning a pre-trained Vision-Language Model with new datasets often falls short in optimizing the vision encoder.<n>We introduce QID, a novel, streamlined, architecture-preserving approach that integrates query embeddings into the vision encoder.
  arXiv  Detail & Related papers  (2025-04-03T18:47:16Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• VISA: Retrieval Augmented Generation with Visual Source Attribution [100.78278689901593]
  Existing approaches in RAG primarily link generated content to document-level references.<n>We propose Retrieval-Augmented Generation with Visual Source Attribution (VISA), a novel approach that combines answer generation with visual source attribution.<n>To evaluate its effectiveness, we curated two datasets: Wiki-VISA, based on crawled Wikipedia webpage screenshots, and Paper-VISA, derived from PubLayNet and tailored to the medical domain.
  arXiv  Detail & Related papers  (2024-12-19T02:17:35Z)
• VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents [66.42579289213941]
  Retrieval-augmented generation (RAG) is an effective technique that enables large language models to utilize external knowledge sources for generation.<n>We introduce VisRAG, which tackles this issue by establishing a vision-language model (VLM)-based RAG pipeline.<n>In this pipeline, instead of first parsing the document to obtain text, the document is directly embedded using a VLM as an image and then retrieved to enhance the generation of a VLM.
  arXiv  Detail & Related papers  (2024-10-14T15:04:18Z)
• ColPali: Efficient Document Retrieval with Vision Language Models [15.369861972085136]
  We introduce the Visual Document Retrieval Benchmark ViDoRe, composed of various page-level retrieval tasks spanning multiple domains, languages, and practical settings.<n>The inherent complexity and performance shortcomings of modern systems motivate a new concept; doing document retrieval by directly embedding the images of the document pages.<n>We release ColPali, a Vision Language Model trained to produce high-quality multi-vector embeddings from images of document pages.
  arXiv  Detail & Related papers  (2024-06-27T15:45:29Z)
• DocumentNet: Bridging the Data Gap in Document Pre-Training [78.01647768018485]
  We propose a method to collect massive-scale and weakly labeled data from the web to benefit the training of VDER models. The collected dataset, named DocumentNet, does not depend on specific document types or entity sets. Experiments on a set of broadly adopted VDER tasks show significant improvements when DocumentNet is incorporated into the pre-training.
  arXiv  Detail & Related papers  (2023-06-15T08:21:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.