DocLLM: A layout-aware generative language model for multimodal document understanding

• URL: http://arxiv.org/abs/2401.00908v1
• Date: Sun, 31 Dec 2023 22:37:52 GMT
• Title: DocLLM: A layout-aware generative language model for multimodal document understanding
• Authors: Dongsheng Wang, Natraj Raman, Mathieu Sibue, Zhiqiang Ma, Petr Babkin, Simerjot Kaur, Yulong Pei, Armineh Nourbakhsh, Xiaomo Liu
• Abstract summary: We present DocLLM, a lightweight extension to traditional large language models (LLMs) for reasoning over visual documents. Our model focuses exclusively on bounding box information to incorporate the spatial layout structure. We demonstrate that our solution outperforms SotA LLMs on 14 out of 16 datasets across all tasks, and generalizes well to 4 out of 5 previously unseen datasets.
• Score: 12.093889265216205
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalities. The visual cues offered by their complex layouts play a crucial role in comprehending these documents effectively. In this paper, we present DocLLM, a lightweight extension to traditional large language models (LLMs) for reasoning over visual documents, taking into account both textual semantics and spatial layout. Our model differs from existing multimodal LLMs by avoiding expensive image encoders and focuses exclusively on bounding box information to incorporate the spatial layout structure. Specifically, the cross-alignment between text and spatial modalities is captured by decomposing the attention mechanism in classical transformers to a set of disentangled matrices. Furthermore, we devise a pre-training objective that learns to infill text segments. This approach allows us to address irregular layouts and heterogeneous content frequently encountered in visual documents. The pre-trained model is fine-tuned using a large-scale instruction dataset, covering four core document intelligence tasks. We demonstrate that our solution outperforms SotA LLMs on 14 out of 16 datasets across all tasks, and generalizes well to 4 out of 5 previously unseen datasets.

Related papers

• Unified Multi-Modal Interleaved Document Representation for Information Retrieval [57.65409208879344]
  We produce more comprehensive and nuanced document representations by holistically embedding documents interleaved with different modalities. Specifically, we achieve this by leveraging the capability of recent vision-language models that enable the processing and integration of text, images, and tables into a unified format and representation.
  arXiv  Detail & Related papers  (2024-10-03T17:49:09Z)
• PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering [13.625303311724757]
  Document Question Answering (QA) presents a challenge in understanding visually-rich documents (VRD) We propose PDF-MVQA, which is tailored for research journal articles, encompassing multiple pages and multimodal information retrieval.
  arXiv  Detail & Related papers  (2024-04-19T09:00:05Z)
• TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models [9.232693392690702]
  TextHawk is a document-oriented Multimodal Large Language Model (MLLM) It is designed to explore efficient fine-grained perception by designing four dedicated components. We conduct extensive experiments on both general and document-oriented MLLM benchmarks, and show that TextHawk outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-04-14T09:48:37Z)
• Visually Guided Generative Text-Layout Pre-training for Document Intelligence [51.09853181377696]
  We propose visually guided generative text-pre-training, named ViTLP. Given a document image, the model optimize hierarchical language and layout modeling objectives to generate the interleaved text and layout sequence. ViTLP can function as a native OCR model to localize and recognize texts of document images.
  arXiv  Detail & Related papers  (2024-03-25T08:00:43Z)
• mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding [100.17063271791528]
  We propose the Unified Structure Learning to boost the performance of MLLMs. Our model DocOwl 1.5 achieves state-of-the-art performance on 10 visual document understanding benchmarks.
  arXiv  Detail & Related papers  (2024-03-19T16:48:40Z)
• LAPDoc: Layout-Aware Prompting for Documents [3.523208537466128]
  We investigate the possibility to use purely text-based LLMs for document-specific tasks by using layout enrichment. Our results indicate that layout enrichment can improve the performance of purely text-based LLMs for document understanding by up to 15%.
  arXiv  Detail & Related papers  (2024-02-15T10:00:49Z)
• DocumentNet: Bridging the Data Gap in Document Pre-Training [78.01647768018485]
  We propose a method to collect massive-scale and weakly labeled data from the web to benefit the training of VDER models. The collected dataset, named DocumentNet, does not depend on specific document types or entity sets. Experiments on a set of broadly adopted VDER tasks show significant improvements when DocumentNet is incorporated into the pre-training.
  arXiv  Detail & Related papers  (2023-06-15T08:21:15Z)
• Cross-Modal Entity Matching for Visually Rich Documents [4.8119678510491815]
  Visually rich documents utilize visual cues to augment their semantics. Existing works that enable structured querying on these documents do not take this into account. We propose Juno -- a cross-modal entity matching framework to address this limitation.
  arXiv  Detail & Related papers  (2023-03-01T18:26:14Z)
• TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents [51.744527199305445]
  This paper proposes a unified end-to-end information extraction framework from visually rich documents. Text reading and information extraction can reinforce each other via a well-designed multi-modal context block. The framework can be trained in an end-to-end trainable manner, achieving global optimization.
  arXiv  Detail & Related papers  (2022-07-14T08:52:07Z)
• Unified Pretraining Framework for Document Understanding [52.224359498792836]
  We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
  arXiv  Detail & Related papers  (2022-04-22T21:47:04Z)
• SelfDoc: Self-Supervised Document Representation Learning [46.22910270334824]
  SelfDoc is a task-agnostic pre-training framework for document image understanding. Our framework exploits the positional, textual, and visual information of every semantically meaningful component in a document. It achieves superior performance on multiple downstream tasks with significantly fewer document images used in the pre-training stage compared to previous works.
  arXiv  Detail & Related papers  (2021-06-07T04:19:49Z)

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.