Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.14381 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915795168133120 |
|---|---|
| author | Ueda, Nobuhiro Dong, Yuyang Boros, Krisztián Ito, Daiki Sera, Takuya Oyamada, Masafumi |
| author_facet | Ueda, Nobuhiro Dong, Yuyang Boros, Krisztián Ito, Daiki Sera, Takuya Oyamada, Masafumi |
| contents | With the increasing adoption of Large Language Models (LLMs) and Vision-Language Models (VLMs), rich document analysis technologies for applications like Retrieval-Augmented Generation (RAG) and visual RAG are gaining significant attention. Recent research indicates that using VLMs yields better RAG performance, but processing rich documents remains a challenge since a single page contains large amounts of information. In this paper, we present SCAN (SemantiC Document Layout ANalysis), a novel approach that enhances both textual and visual Retrieval-Augmented Generation (RAG) systems that work with visually rich documents. It is a VLM-friendly approach that identifies document components with appropriate semantic granularity, balancing context preservation with processing efficiency. SCAN uses a coarse-grained semantic approach that divides documents into coherent regions covering contiguous components. We trained the SCAN model by fine-tuning object detection models on an annotated dataset. Our experimental results across English and Japanese datasets demonstrate that applying SCAN improves end-to-end textual RAG performance by up to 9.4 points and visual RAG performance by up to 10.4 points, outperforming conventional approaches and even commercial document processing solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14381 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation Ueda, Nobuhiro Dong, Yuyang Boros, Krisztián Ito, Daiki Sera, Takuya Oyamada, Masafumi Artificial Intelligence With the increasing adoption of Large Language Models (LLMs) and Vision-Language Models (VLMs), rich document analysis technologies for applications like Retrieval-Augmented Generation (RAG) and visual RAG are gaining significant attention. Recent research indicates that using VLMs yields better RAG performance, but processing rich documents remains a challenge since a single page contains large amounts of information. In this paper, we present SCAN (SemantiC Document Layout ANalysis), a novel approach that enhances both textual and visual Retrieval-Augmented Generation (RAG) systems that work with visually rich documents. It is a VLM-friendly approach that identifies document components with appropriate semantic granularity, balancing context preservation with processing efficiency. SCAN uses a coarse-grained semantic approach that divides documents into coherent regions covering contiguous components. We trained the SCAN model by fine-tuning object detection models on an annotated dataset. Our experimental results across English and Japanese datasets demonstrate that applying SCAN improves end-to-end textual RAG performance by up to 9.4 points and visual RAG performance by up to 10.4 points, outperforming conventional approaches and even commercial document processing solutions. |
| title | SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2505.14381 |