Query-Driven Multimodal Information Extraction from Long Documents

• URL: http://arxiv.org/abs/2608.22214v1
• Date: Sun, 23 Aug 2026 04:37:34 GMT
• Title: Query-Driven Multimodal Information Extraction from Long Documents
• Abstract summary: We propose query-driven image-text joint extraction from long documents.<n>Based on challenges related to both user intent and document content, we designed a two-level taxonomy.<n>We construct ITJoint, the first high-quality, manually annotated benchmark for this new task.
• Score: 6.155740787063792
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. However, existing paradigms like DocVQA primarily focus on generating textual answers or localizing evidence regions, rather than outputting query-specific textual attribute values and corresponding images. To address this gap, we propose query-driven image-text joint extraction from long documents, requiring models to output query-requested textual attribute values and corresponding image bounding boxes. Based on challenges related to both user intent and document content, we designed a two-level taxonomy that operates at the query and instance levels. Further, we construct ITJoint, the first high-quality, manually annotated benchmark for this new task, comprising 2,455 pages of domain-specific documents with numerous non-decorative images, 316 queries, and 910 answer instances. Finally, we evaluate representative standalone Vision-Language Models from different providers and further design Q2IT, a multi-agent collaborative framework consisting of three progressively collaborating agents for evidence collection, page selection, and target-image localization. Using a joint evaluation approach that assesses both text extraction and image localization, our experiments show that standalone VLMs struggle with this task, while Q2IT significantly improves performance on ITJoint, although a substantial gap remains toward perfect results.

Related papers

• Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment [57.41731607488101]
  TIC-Bench is designed to evaluate the capability of models to integrate text-image clues and recover the ground truth facts within deeply interleaved contexts.<n>We evaluated 10 state-of-the-art MLLMs and observed a substantial performance gap compared to human experts.
  arXiv  Detail & Related papers  (2026-09-02T13:19:51Z)
• VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA [7.046359260432822]
  We introduce VinQA, a dataset for long-form answer generation where cited visual elements are explicitly interleaved with their supporting text.<n>We study two encoding methods for feeding raw document page images into an MLLM, along with their visual-element citation mechanisms.<n>In our experiments, we propose M-GroSE to assess answers along four dimensions: completeness, answer relevancy, faithfulness, and unability.
  arXiv  Detail & Related papers  (2026-06-15T01:14:14Z)
• Seeing Through Words: Controlling Visual Retrieval Quality with Language Models [68.49490036960559]
  We propose a new paradigm of quality-controllable retrieval, which enriches short queries with contextual details while incorporating explicit notions of image quality.<n>Our key idea is to leverage a generative language model as a query completion function, extending underspecified queries into descriptive forms.<n>Our proposed approach significantly improves retrieval results and provides effective quality control, bridging the gap between the expressive capacity of modern VLMs and the underspecified nature of short user queries.
  arXiv  Detail & Related papers  (2026-02-24T18:20:57Z)
• CMRAG: Co-modality-based visual document retrieval and question answering [21.016544020685668]
  Co-Modality-based RAG (RAG) framework can leverage texts and images for more accurate retrieval and generation.<n>Our framework consistently outperforms single-modality-based RAG in multiple visual document question-answering (VDQA) benchmarks.
  arXiv  Detail & Related papers  (2025-09-02T09:17:57Z)
• 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)
• 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)
• FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion [7.322448493179106]
  Flow Text with Image Insertion task requires LVLMs to simultaneously possess outstanding abilities in image comprehension, instruction understanding, and long-text interpretation. We introduce the Flow Text with Image Insertion Benchmark (FTII-Bench), which includes 318 high-quality Chinese image-text news articles and 307 high-quality English image-text news articles, covering 10 different news domains. We evaluate 9 open-source and 2 closed-source LVLMs as well as 2 CLIP-based models.
  arXiv  Detail & Related papers  (2024-10-16T13:38:31Z)
• Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks [62.758680527838436]
  We propose Leopard, an MLLM tailored for handling vision-language tasks involving multiple text-rich images.<n>First, we curated about one million high-quality multimodal instruction-tuning data, tailored to text-rich, multi-image scenarios.<n>Second, we proposed an adaptive high-resolution multi-image encoding module to dynamically optimize the allocation of visual sequence length.
  arXiv  Detail & Related papers  (2024-10-02T16:55:01Z)
• OpenLEAF: Open-Domain Interleaved Image-Text Generation and Evaluation [151.57313182844936]
  We propose a new interleaved generation framework based on prompting large-language models (LLMs) and pre-trained text-to-image (T2I) models, namely OpenLEAF. For model assessment, we first propose to use large multi-modal models (LMMs) to evaluate the entity and style consistencies of open-domain interleaved image-text sequences.
  arXiv  Detail & Related papers  (2023-10-11T17:58:33Z)
• DUBLIN -- Document Understanding By Language-Image Network [37.42637168606938]
  We propose DUBLIN, which is pretrained on web pages using three novel objectives. We show that DUBLIN is the first pixel-based model to achieve an EM of 77.75 and F1 of 84.25 on the WebSRC dataset. We also achieve competitive performance on RVL-CDIP document classification.
  arXiv  Detail & Related papers  (2023-05-23T16:34:09Z)
• Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark [80.79082788458602]
  We provide a new multi-task benchmark for evaluating text-to-image models. We compare the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students evaluated the two models, on three tasks, at three difficulty levels, across ten prompts each.
  arXiv  Detail & Related papers  (2022-11-22T09:27:53Z)
• ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity [16.550790981646276]
  Current approaches combine the features of each of the two elements of the query into a single representation. Our work aims at shedding new light on the task by looking at it through the prism of two familiar and related frameworks: text-to-image and image-to-image retrieval.
  arXiv  Detail & Related papers  (2022-03-15T17:29:20Z)

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.