DocMMIR: A Framework for Document Multi-modal Information Retrieval

• URL: http://arxiv.org/abs/2505.19312v2
• Date: Thu, 29 May 2025 13:14:43 GMT
• Title: DocMMIR: A Framework for Document Multi-modal Information Retrieval
• Authors: Zirui Li, Siwei Wu, Xingyu Wang, Yi Zhou, Yizhi Li, Chenghua Lin,
• Abstract summary: We introduce DocMMIR, a novel multi-modal document retrieval framework.<n>We construct a large-scale cross-domain multimodal benchmark, comprising 450K samples.<n>Results show a +31% improvement in MRR@10 compared to the zero-shot baseline.
• Score: 21.919132888183622
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid advancement of unsupervised representation learning and large-scale pre-trained vision-language models has significantly improved cross-modal retrieval tasks. However, existing multi-modal information retrieval (MMIR) studies lack a comprehensive exploration of document-level retrieval and suffer from the absence of cross-domain datasets at this granularity. To address this limitation, we introduce DocMMIR, a novel multi-modal document retrieval framework designed explicitly to unify diverse document formats and domains, including Wikipedia articles, scientific papers (arXiv), and presentation slides, within a comprehensive retrieval scenario. We construct a large-scale cross-domain multimodal benchmark, comprising 450K samples, which systematically integrates textual and visual information. Our comprehensive experimental analysis reveals substantial limitations in current state-of-the-art MLLMs (CLIP, BLIP2, SigLIP-2, ALIGN) when applied to our tasks, with only CLIP demonstrating reasonable zero-shot performance. Furthermore, we conduct a systematic investigation of training strategies, including cross-modal fusion methods and loss functions, and develop a tailored approach to train CLIP on our benchmark. This results in a +31% improvement in MRR@10 compared to the zero-shot baseline. All our data and code are released in https://github.com/J1mL1/DocMMIR.

Related papers

• Docopilot: Improving Multimodal Models for Document-Level Understanding [87.60020625241178]
  We present a high-quality document-level dataset, Doc-750K, designed to support in-depth understanding of multimodal documents.<n>This dataset includes diverse document structures, extensive cross-page dependencies, and real question-answer pairs derived from the original documents.<n>Building on the dataset, we develop a native multimodal model, Docopilot, which can accurately handle document-level dependencies without relying on RAG.
  arXiv  Detail & Related papers  (2025-07-19T16:03:34Z)
• Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval [33.70775865228575]
  We introduce UNITE, a universal framework that tackles challenges through data curation and modality-aware training configurations.<n>Our work provides the first comprehensive analysis of how modality-specific data properties influence downstream task performance.<n>Our framework achieves state-of-the-art results on multiple multimodal retrieval benchmarks, outperforming existing methods by notable margins.
  arXiv  Detail & Related papers  (2025-05-26T08:09:44Z)
• Doc-CoB: Enhancing Multi-Modal Document Understanding with Visual Chain-of-Boxes Reasoning [12.17399365931]
  Existing one-pass MLLMs process entire document images without considering query relevance.<n>Inspired by the human coarse-to-fine reading pattern, we introduce Doc-CoB, a simple-yet-effective mechanism that integrates human-style visual reasoning into MLLM.<n>Our method allows the model to autonomously select the set of regions most relevant to the query, and then focus attention on them for further understanding.
  arXiv  Detail & Related papers  (2025-05-24T08:53:05Z)
• A Multi-Granularity Retrieval Framework for Visually-Rich Documents [4.804551482123172]
  We propose a unified multi-granularity multimodal retrieval framework tailored for two benchmark tasks: MMDocIR and M2KR.<n>Our approach integrates hierarchical encoding strategies, modality-aware retrieval mechanisms, and vision-language model (VLM)-based candidate filtering.<n>Our framework demonstrates robust performance without the need for task-specific fine-tuning.
  arXiv  Detail & Related papers  (2025-05-01T02:40:30Z)
• M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization? [49.53982792497275]
  We investigate whether Large Vision-Language Models (LVLMs) genuinely comprehend interleaved image-text in the document.<n>Existing document understanding benchmarks often assess LVLMs using question-answer formats.<n>We introduce a novel and challenging Multimodal Document Summarization Benchmark (M-DocSum-Bench)<n>M-DocSum-Bench comprises 500 high-quality arXiv papers, along with interleaved multimodal summaries aligned with human preferences.
  arXiv  Detail & Related papers  (2025-03-27T07:28:32Z)
• Composed Multi-modal Retrieval: A Survey of Approaches and Applications [81.54640206021757]
  Composed Multi-modal Retrieval (CMR) emerges as a pivotal next-generation technology.<n>CMR enables users to query images or videos by integrating a reference visual input with textual modifications.<n>This paper provides a comprehensive survey of CMR, covering its fundamental challenges, technical advancements, and applications.
  arXiv  Detail & Related papers  (2025-03-03T09:18:43Z)
• Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts [56.30364248231053]
  This paper introduces Multi-Modal Retrieval-Augmented Generation (M2RAG)<n>M2RAG is a benchmark designed to evaluate the effectiveness of Multi-modal Large Language Models (MLLMs)<n>To enhance the context utilization capabilities of MLLMs, we also introduce Multi-Modal Retrieval-Augmented Instruction Tuning (MM-RAIT)
  arXiv  Detail & Related papers  (2025-02-24T16:25:25Z)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation [19.745059794932807]
  We introduce the Multimodal Retrieval-Augmented Multimodal Generation (MRAMG) task.<n>We aim to generate multimodal answers that combine both text and images, fully leveraging the multimodal data within a corpus.<n>To facilitate rigorous evaluation, MRAMG-Bench incorporates a comprehensive suite of both statistical and LLM-based metrics.
  arXiv  Detail & Related papers  (2025-02-06T16:07:24Z)
• VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation [100.06122876025063]
  This paper introduces VisDoMBench, the first comprehensive benchmark designed to evaluate QA systems in multi-document settings.<n>We propose VisDoMRAG, a novel multimodal Retrieval Augmented Generation (RAG) approach that simultaneously utilizes visual and textual RAG.
  arXiv  Detail & Related papers  (2024-12-14T06:24:55Z)
• MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs [78.5013630951288]
  This paper introduces techniques for advancing information retrieval with multimodal large language models (MLLMs)<n>We first study fine-tuning an MLLM as a bi-encoder retriever on 10 datasets with 16 retrieval tasks.<n>Our model, MM-Embed, achieves state-of-the-art performance on the multimodal retrieval benchmark M-BEIR.
  arXiv  Detail & Related papers  (2024-11-04T20:06:34Z)

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.