---
title: "MM-RAG (Multimodal RAG) — 多模态RAG"
source: "https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG"
wiki: "systems-analysis.info/int"
article: "MM-RAG_(Multimodal_RAG)_—_多模态RAG"
language: "zh"
categories:
  - "Category:Chinese"
  - "Category:Large language models"
  - "Category:Prompt engineering"
revision_id: 4066
wiki_created_at: 2026-09-06T23:30:00Z
wiki_modified_at: 2026-09-06T23:30:00Z
downloaded_at: 2026-09-07T23:00:41Z
---

# MM-RAG (Multimodal RAG) — 多模态RAG

**MM-RAG** (英文：*Multimodal Retrieval-Augmented Generation*，多模态检索增强生成) 是经典RAG范式的扩展。在这种范式中，LLM不仅使用文本，还利用视觉数据（图像、图表、表格、图形）来生成回答。多模态检索能够查找并关联不同形式的证据，通过依赖外部来源，并将信息精确定位到页面片段和区域（*bounding boxes*，边界框），从而降低了产生幻觉的风险<sup>[\[1\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-lewis2020-1)[\[2\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-visrag2024-2)</sup>。

MM-RAG 对于大部分信息以非文本形式（如页面布局、图表、表格结构）呈现的文档尤其有用。在这类情况下，经典的纯文本 RAG 常常会丢失重要的上下文元素<sup>[\[3\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-docvqa2021-3)[\[4\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-textvqa2019-4)</sup>。

## 背景与待解决的问题

经典 RAG 处理的是文本段落，无法识别视觉结构（如元素布局、图片标题、图表坐标轴）。MM-RAG 填补了这些空白：它提取结构化元素（文本、表格、带坐标的图像），将其索引到向量空间中，并结合来自不同模态的证据<sup>[\[5\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-layoutlm2020-5)[\[6\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-clip2021-6)</sup>。

## MM-RAG 架构

MM-RAG 的工作流在经典 RAG 的基础上增加了视觉数据处理和模态对齐的步骤：**数据注入 (Ingestion) → 索引 (Indexing) → 多模态检索 (Multimodal Retrieval) → 融合与重排 (Fusion & Reranking) → 可追溯生成 (Generation with Tracing)**。

1.  **数据采集与预处理 (Ingestion)**：输入 PDF、扫描件或图像。系统执行 OCR 和页面**布局分析**，以识别并划分区域：段落、标题、表格、图像及其坐标。常用工具包括 LayoutLM 系列模型和 LayoutParser 工具库；验证和训练通常依赖于 PubLayNet 和 DocLayNet 数据集<sup>[\[7\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-publaynet2019-7)[\[8\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-doclaynet2022-8)[\[9\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-layoutparser2021-9)</sup>。
2.  **区域分割**：提取视觉对象（图表、表格、插图、标题）。为提高鲁棒性，可采用无需 OCR 的模型（如 Donut）或 OCR+VLM 的组合流水线<sup>[\[10\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-donut2021-10)</sup>。
3.  **索引 (Vector Index)**：将文本块和视觉元素（图像或其描述）转换为向量表示，并存入向量数据库。为了建立统一的*文本↔图像*空间，通常使用 CLIP 或 SigLIP；在生产环境中，多模态/多向量索引（一个对象对应多个向量）更为便捷<sup>[\[6\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-clip2021-6)[\[11\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-siglip2023-11)[\[12\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-milvus-mv-12)</sup>。
4.  **多模态检索与重排**：结合文本和视觉搜索；将候选结果（段落、表格、图像/区域）合并，并使用更“重”的模型（如交叉编码器/LLM 重排器）进行重排，以提高准确性<sup>[\[13\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-cohere-rerank-13)</sup>。
5.  **上下文打包与生成**：将筛选出的片段输入 LLM/VLM。如果模型是多模态的（如 GPT-4V/4o），图像可以直接输入；如果使用纯文本 LLM，图像则需要预先转换为详细描述<sup>[\[14\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-gpt4v-14)[\[15\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-gpt4o-15)</sup>。
6.  **追溯与引用**：生成的回答附带可点击的引用，不仅链接到文档/页面，还能精确定位到具体区域（坐标）。这提升了*grounding*（信息溯源）水平和用户信任度<sup>[\[2\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-visrag2024-2)</sup>。

## 质量评估与指标

MM-RAG 的有效性从提取、检索和生成三个层面进行评估。

- **视觉数据提取质量**：在 DocLayNet/PubLayNet 等数据集上评估 OCR 准确率（WER/CER）和布局分析质量（mAP/Precision/Recall）<sup>[\[8\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-doclaynet2022-8)[\[7\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-publaynet2019-7)</sup>。
- **检索质量**：采用标准信息检索指标：Recall@K、Precision@K、MRR；对于多模态，需分别评估各模态及组合后的效果。
- **端到端回答质量**：使用自动化指标 *faithfulness*/*groundedness* 以及人工评估。实践中常使用 RAGAS/TruLens/DeepEval 等框架<sup>[\[16\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-ragas-16)</sup>。
- **基准测试 (Benchmarks)**：
  - **DocVQA**：针对文档图像的问答<sup>[\[3\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-docvqa2021-3)</sup>。
  - **TextVQA**：需要读取图像中文本才能回答的问题<sup>[\[4\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-textvqa2019-4)</sup>。
  - **InfographicVQA**：针对信息图表的问答<sup>[\[17\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-infographicvqa2021-17)</sup>。
  - **ChartQA**：针对图表的问答，需要逻辑推理<sup>[\[18\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-chartqa2022-18)</sup>。
  - **MMDocRAG**：用于文档问答（DocQA）的多模态 RAG 基准测试，包含多页文档和跨模态证据链<sup>[\[19\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-mmdocrag2025-19)</sup>。

## 组件对比表

| 组件       | 实现方案                                               | 优点                                                                            | 缺点 / 风险                                                | 选择建议                                                                      |
|------------|--------------------------------------------------------|---------------------------------------------------------------------------------|------------------------------------------------------------|-------------------------------------------------------------------------------|
| OCR        | Tesseract / PaddleOCR / 云服务 API                     | 本地部署方案保护隐私且可控；云服务则提供开箱即用的高精度。                      | 复杂布局可能导致识别错误；API 方案有成本和合规性要求。     | 涉密数据采用本地 OCR；追求最高精度则使用云服务（若合规）。                    |
| 布局分析   | 规则 / 机器学习模型 (LayoutLM, LayoutParser)           | 规则对标准化模板简单有效；机器学习对多样化布局鲁棒性强。                        | 规则在处理新布局时容易失效；机器学习则需要计算资源和数据。 | 标准化表单使用规则；多样化文档库则采用机器学习。                              |
| 图像向量化 | CLIP / SigLIP / 无需 OCR 的描述生成 (Donut/Pix2Struct) | CLIP/SigLIP 提供统一的*文本↔图像*潜在空间；无需 OCR 的方法摆脱了对 OCR 的依赖。 | CLIP 无法读取图像内的文本；而文本描述可能会歪曲原意。      | CLIP/SigLIP 用于基础多模态搜索；对于质量较差的扫描件，可采用无需 OCR 的方法。 |
| 结果融合   | 按分数排序 / 按模态分配配额 / LLM 重排器               | 重排器能显著提高上下文选择的准确性。                                            | 增加延迟和成本。                                           | 高精度场景；简单方法适用于概念验证 (PoC)。                                    |
| 存储/索引  | 单向量 / 多向量 (文本+图像) / 混合索引 (BM25+向量)     | 多向量索引能覆盖同一对象的不同表示；混合搜索则能有效处理关键词和代码。          | 方案和更新流程更复杂。                                     | 适用于混合数据和有严格服务等级协议 (SLA) 的生产系统。                         |

MM-RAG 关键组件与方法对比

## 实践说明

- **混合搜索** (BM25 + 向量)：事实上已成为提高特定术语/代码检索召回率和准确率的标准方法<sup>[\[20\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-weaviate-hybrid-20)</sup>。
- **重排**：使用交叉编码器/LLM进行重排，可以在生成前过滤掉“垃圾”候选，从而节省 token<sup>[\[13\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-cohere-rerank-13)</sup>。
- **现代 VLM 检索器**（例如 ColPali）通过直接索引页面图像，在视觉内容丰富的文档上展现出优势<sup>[\[21\]](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_note-colpali2024-21)</sup>。

## 参见

- Retrieval-Augmented Generation
- 向量数据库
- Embedding
- GraphRAG

## 参考文献

- Lewis, P. et al. (2020). *Retrieval‑Augmented Generation for Knowledge‑Intensive NLP Tasks*. NeurIPS. <a href="https://arxiv.org/abs/2005.11401" class="external text" rel="nofollow">arXiv:2005.11401</a>.
- Gao, L. et al. (2023). *Precise Zero‑Shot Dense Retrieval without Relevance Labels (HyDE)*. ACL 2023. <a href="https://arxiv.org/abs/2212.10496" class="external text" rel="nofollow">arXiv:2212.10496</a>.
- Mei, L., Mo, S., Yang, Z., Chen, C. (2025). *A Survey of Multimodal Retrieval‑Augmented Generation*. <a href="https://arxiv.org/abs/2504.08748" class="external text" rel="nofollow">arXiv:2504.08748</a>.
- Abootorabi, M.M. et al. (2025). *Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval‑Augmented Generation*. Findings of ACL 2025. <a href="https://aclanthology.org/2025.findings-acl.861/" class="external text" rel="nofollow">ACL Anthology</a>.
- Yu, S. et al. (2024). *VisRAG: Vision‑based Retrieval‑augmented Generation on Multi‑modality Documents*. <a href="https://arxiv.org/abs/2410.10594" class="external text" rel="nofollow">arXiv:2410.10594</a>.
- Cho, J. et al. (2024). *M3DocRAG: Multi‑modal Retrieval is What You Need for Multi‑document QA*. <a href="https://arxiv.org/abs/2411.04952" class="external text" rel="nofollow">arXiv:2411.04952</a>.
- Tanaka, R. et al. (2025). *VDocRAG: Retrieval‑Augmented Generation over Visually‑Rich Documents*. CVPR 2025. <a href="https://arxiv.org/abs/2504.09795" class="external text" rel="nofollow">arXiv:2504.09795</a> • <a href="https://openaccess.thecvf.com/content/CVPR2025/papers/Tanaka_VDocRAG_Retrieval-Augmented_Generation_over_Visually-Rich_Documents_CVPR_2025_paper.pdf" class="external text" rel="nofollow">CVF Open Access</a>.
- Dong, K. et al. (2025). *MMDocRAG: Benchmarking Retrieval‑Augmented Multimodal Generation for Document Question Answering*. <a href="https://arxiv.org/abs/2505.16470" class="external text" rel="nofollow">arXiv:2505.16470</a>.
- Wasserman, N. et al. (2025). *REAL‑MM‑RAG: A Real‑World Multi‑Modal Retrieval Benchmark*. <a href="https://arxiv.org/abs/2502.12342" class="external text" rel="nofollow">arXiv:2502.12342</a>.
- Faysse, M. et al. (2024). *ColPali: Efficient Document Retrieval with Vision Language Models*. <a href="https://arxiv.org/abs/2407.01449" class="external text" rel="nofollow">arXiv:2407.01449</a>.
- Radford, A. et al. (2021). *Learning Transferable Visual Models From Natural Language Supervision (CLIP)*. ICML 2021. <a href="https://arxiv.org/abs/2103.00020" class="external text" rel="nofollow">arXiv:2103.00020</a>.
- Tschannen, M. et al. (2025). *SigLIP 2: Multilingual Vision‑Language Encoders with Improved Semantic Understanding, Localization, and Dense Features*. <a href="https://arxiv.org/abs/2502.14786" class="external text" rel="nofollow">arXiv:2502.14786</a>.
- Xu, Y. et al. (2020). *LayoutLM: Pre‑training of Text and Layout for Document Image Understanding*. KDD 2020. <a href="https://dl.acm.org/doi/10.1145/3394486.3403172" class="external text" rel="nofollow">DOI</a> • <a href="https://arxiv.org/abs/1912.13318" class="external text" rel="nofollow">arXiv:1912.13318</a>.
- Huang, Y. et al. (2022). *LayoutLMv3: Pre‑training for Document AI with Unified Text and Image Masking*. <a href="https://arxiv.org/abs/2204.08387" class="external text" rel="nofollow">arXiv:2204.08387</a>.
- Zhong, X., Tang, J., Jimeno‑Yepes, A.J. (2019). *PubLayNet: Largest Dataset Ever for Document Layout Analysis*. <a href="https://arxiv.org/abs/1908.07836" class="external text" rel="nofollow">arXiv:1908.07836</a>.
- Pfitzmann, B. et al. (2022). *DocLayNet: A Large Human‑Annotated Dataset for Document‑Layout Analysis*. <a href="https://arxiv.org/abs/2206.01062" class="external text" rel="nofollow">arXiv:2206.01062</a>.
- Kim, G. et al. (2021). *OCR‑free Document Understanding Transformer (Donut)*. <a href="https://arxiv.org/abs/2111.15664" class="external text" rel="nofollow">arXiv:2111.15664</a>.
- Shen, Z. et al. (2021). *LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis*. <a href="https://arxiv.org/abs/2103.15348" class="external text" rel="nofollow">arXiv:2103.15348</a>.
- Singh, A. et al. (2019). *Towards VQA Models That Can Read (TextVQA)*. CVPR 2019. <a href="https://arxiv.org/abs/1904.08920" class="external text" rel="nofollow">arXiv:1904.08920</a>.
- Mathew, M. et al. (2021/2022). *DocVQA / InfographicVQA: Datasets for VQA on Document Images and Infographics*. WACV 2021 / WACV 2022. <a href="https://openaccess.thecvf.com/content/WACV2021/html/Mathew_DocVQA_A_Dataset_for_VQA_on_Document_Images_WACV_2021_paper.html" class="external text" rel="nofollow">CVF</a> • <a href="https://arxiv.org/abs/2104.12756" class="external text" rel="nofollow">arXiv:2104.12756</a>.
- Masry, A. et al. (2022). *ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning*. Findings of ACL 2022. <a href="https://aclanthology.org/2022.findings-acl.177/" class="external text" rel="nofollow">ACL</a> • <a href="https://arxiv.org/abs/2203.10244" class="external text" rel="nofollow">arXiv:2203.10244</a>.
- Liu, F. et al. (2022). *DePlot: One‑shot Visual Language Reasoning by Plot‑to‑Table Translation*. <a href="https://arxiv.org/abs/2212.10505" class="external text" rel="nofollow">arXiv:2212.10505</a>.
- Wang, P. et al. (2024). *Qwen2‑VL: Enhancing Vision‑Language Model’s Capabilities in OCR and Chart QA*. <a href="https://arxiv.org/abs/2409.12191" class="external text" rel="nofollow">arXiv:2409.12191</a>.
- Es, S. et al. (2023). *RAGAS: Automated Evaluation of Retrieval‑Augmented Generation*. <a href="https://arxiv.org/abs/2309.15217" class="external text" rel="nofollow">arXiv:2309.15217</a>.

## 注释

1.  <span id="cite_note-lewis2020-1">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-lewis2020_1-0) Lewis, P., Perez, E., et al. (2020). *Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks*. NeurIPS. <a href="https://arxiv.org/abs/2005.11401" class="external text" rel="nofollow">arXiv:2005.11401</a>.</span>
2.  <span id="cite_note-visrag2024-2">↑ <sup>[2.0](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-visrag2024_2-0)</sup> <sup>[2.1](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-visrag2024_2-1)</sup> Yu, S. et al. (2024). *VisRAG: Vision-based Retrieval-Augmented Generation on Multi-modality Documents*. <a href="https://arxiv.org/abs/2407.06437" class="external text" rel="nofollow">arXiv:2407.06437</a>.</span>
3.  <span id="cite_note-docvqa2021-3">↑ <sup>[3.0](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-docvqa2021_3-0)</sup> <sup>[3.1](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-docvqa2021_3-1)</sup> Mathew, M. et al. (2021). *DocVQA: A Dataset for VQA on Document Images*. WACV. <a href="https://arxiv.org/abs/2007.00398" class="external text" rel="nofollow">arXiv:2007.00398</a>.</span>
4.  <span id="cite_note-textvqa2019-4">↑ <sup>[4.0](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-textvqa2019_4-0)</sup> <sup>[4.1](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-textvqa2019_4-1)</sup> Singh, A. et al. (2019). *TextVQA: Towards VQA Models That Can Read*. CVPR. <a href="https://arxiv.org/abs/1904.08920" class="external text" rel="nofollow">arXiv:1904.08920</a>.</span>
5.  <span id="cite_note-layoutlm2020-5">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-layoutlm2020_5-0) Xu, Y. et al. (2020). *LayoutLM: Pre-training of Text and Layout for Document Image Understanding*. KDD. <a href="https://dl.acm.org/doi/10.1145/3394486.3403172" class="external text" rel="nofollow">DOI</a>.</span>
6.  <span id="cite_note-clip2021-6">↑ <sup>[6.0](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-clip2021_6-0)</sup> <sup>[6.1](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-clip2021_6-1)</sup> Radford, A. et al. (2021). *Learning Transferable Visual Models From Natural Language Supervision (CLIP)*. ICML. <a href="https://arxiv.org/abs/2103.00020" class="external text" rel="nofollow">arXiv:2103.00020</a>.</span>
7.  <span id="cite_note-publaynet2019-7">↑ <sup>[7.0](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-publaynet2019_7-0)</sup> <sup>[7.1](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-publaynet2019_7-1)</sup> Zhong, X., Tang, J., Yepes, A. J. (2019). *PubLayNet: Largest Dataset for Document Layout Analysis*. ICDAR. <a href="https://arxiv.org/abs/1908.07836" class="external text" rel="nofollow">arXiv:1908.07836</a>.</span>
8.  <span id="cite_note-doclaynet2022-8">↑ <sup>[8.0](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-doclaynet2022_8-0)</sup> <sup>[8.1](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-doclaynet2022_8-1)</sup> Pfitzmann, B. et al. (2022). *DocLayNet: A Large Human‑Annotated Dataset for Document‑Layout Analysis*. KDD. <a href="https://dl.acm.org/doi/10.1145/3534678.3539043" class="external text" rel="nofollow">DOI</a> / <a href="https://arxiv.org/abs/2206.01062" class="external text" rel="nofollow">arXiv:2206.01062</a>.</span>
9.  <span id="cite_note-layoutparser2021-9">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-layoutparser2021_9-0) Shen, Z. et al. (2021). *LayoutParser: A Unified Toolkit for DL‑based Document Image Analysis*. <a href="https://arxiv.org/abs/2103.15348" class="external text" rel="nofollow">arXiv:2103.15348</a>.</span>
10. <span id="cite_note-donut2021-10">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-donut2021_10-0) Kim, G. et al. (2021). *Donut: OCR‑free Document Understanding Transformer*. <a href="https://arxiv.org/abs/2111.15664" class="external text" rel="nofollow">arXiv:2111.15664</a>.</span>
11. <span id="cite_note-siglip2023-11">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-siglip2023_11-0) Zhai, X. et al. (2023). *Sigmoid Loss for Language‑Image Pre‑Training (SigLIP)*. ICCV. <a href="https://arxiv.org/abs/2303.15343" class="external text" rel="nofollow">arXiv:2303.15343</a>.</span>
12. <span id="cite_note-milvus-mv-12">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-milvus-mv_12-0) Milvus Docs. *Multi‑Vector Hybrid Search*. <a href="https://milvus.io/docs/multi-vector-search.md" class="external text" rel="nofollow">milvus.io/docs/multi-vector-search.md</a>.</span>
13. <span id="cite_note-cohere-rerank-13">↑ <sup>[13.0](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-cohere-rerank_13-0)</sup> <sup>[13.1](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-cohere-rerank_13-1)</sup> Cohere Docs. *Rerank API*. <a href="https://docs.cohere.com/reference/rerank" class="external text" rel="nofollow">docs.cohere.com/reference/rerank</a>.</span>
14. <span id="cite_note-gpt4v-14">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-gpt4v_14-0) OpenAI. *GPT‑4V(ision) System Card*. (2023). <a href="https://cdn.openai.com/papers/GPTV_System_Card.pdf" class="external text" rel="nofollow">PDF</a>.</span>
15. <span id="cite_note-gpt4o-15">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-gpt4o_15-0) OpenAI. *Hello GPT‑4o*. (2024). <a href="https://openai.com/index/hello-gpt-4o/" class="external text" rel="nofollow">openai.com/index/hello-gpt-4o/</a>.</span>
16. <span id="cite_note-ragas-16">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-ragas_16-0) Es, S. et al. (2023). *RAGAS: Automated Evaluation of Retrieval Augmented Generation*. <a href="https://arxiv.org/abs/2309.15217" class="external text" rel="nofollow">arXiv:2309.15217</a>.</span>
17. <span id="cite_note-infographicvqa2021-17">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-infographicvqa2021_17-0) Mathew, M. et al. (2021). *InfographicVQA: Understanding Infographics via Question Answering*. ICDAR. <a href="https://arxiv.org/abs/2104.12756" class="external text" rel="nofollow">arXiv:2104.12756</a>.</span>
18. <span id="cite_note-chartqa2022-18">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-chartqa2022_18-0) Masry, A. et al. (2022). *ChartQA: A Benchmark for Question Answering about Charts*. ACL (Findings). <a href="https://arxiv.org/abs/2103.16435" class="external text" rel="nofollow">arXiv:2103.16435</a>.</span>
19. <span id="cite_note-mmdocrag2025-19">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-mmdocrag2025_19-0) Dong, K. et al. (2025). *Benchmarking Retrieval‑Augmented Multimodal Generation for Document QA (MMDocRAG)*. <a href="https://arxiv.org/abs/2505.16470" class="external text" rel="nofollow">arXiv:2505.16470</a>.</span>
20. <span id="cite_note-weaviate-hybrid-20">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-weaviate-hybrid_20-0) Weaviate Docs. *Hybrid search*. <a href="https://docs.weaviate.io/weaviate/concepts/search/hybrid-search" class="external text" rel="nofollow">docs.weaviate.io/.../hybrid-search</a>.</span>
21. <span id="cite_note-colpali2024-21">[↑](https://systems-analysis.info/int/MM-RAG_(Multimodal_RAG)_%E2%80%94_%E5%A4%9A%E6%A8%A1%E6%80%81RAG#cite_ref-colpali2024_21-0) Faysse, M. et al. (2024). *ColPali: Efficient Document Retrieval with Vision‑Language Models*. <a href="https://arxiv.org/abs/2407.01449" class="external text" rel="nofollow">arXiv:2407.01449</a>.</span>
