# DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark

arXiv: https://arxiv.org/abs/2605.30027 · HTML: https://mlsanity.com/paper/2605.30027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 76 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 30 of 41)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://mlsanity.com/paper/2407.19669/) (2024)
- [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://mlsanity.com/paper/2410.05160/) (2024)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading](https://mlsanity.com/paper/2310.05029/) (2023)
- [Unifying Multimodal Retrieval via Document Screenshot Embedding](https://mlsanity.com/paper/2406.11251/) (2024)
- [Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models](https://mlsanity.com/paper/2103.15543/) (2021)
- [Towards Complex Document Understanding By Discrete Reasoning](https://mlsanity.com/paper/2207.11871/) (2022)
- [ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval](https://mlsanity.com/paper/2505.17166/) (2025)
- [MMDocIR: Benchmarking Multimodal Retrieval for Long Documents](https://mlsanity.com/paper/2501.08828/) (2025)

## Abstract (arXiv)

Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve high-precision retrieval, they face inherent limitations. First, the coarse-grained nature of dense embeddings tends to obfuscate explicit semantics, failing to leverage structurally salient information. Second, supervised reranking models suffer from generalization bottlenecks, as their performance heavily relies on domain-specific training data. Furthermore, existing benchmarks often lack diverse assessment dimensions and comprehensive relevance annotations, limiting reliable evaluation. To address these challenges, we propose DocRetriever, a plug-and-play framework. It enhances visual retrieval via a layout-aware sparse embedding technique, enabling effective hybrid encoding without the overhead of optical character recognition (OCR). We also introduce a generalizable reranker that leverages reasoning-augmented demonstrations and optimized sampling to improve accuracy in few-shot settings. Finally, we construct a new benchmark, MultiDocR, to enable more rigorous evaluation. Experiments across diverse benchmarks validate DocRetriever's superiority over state-of-the-art methods.