Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments

• URL: http://arxiv.org/abs/2505.13535v1
• Date: Sun, 18 May 2025 15:49:17 GMT
• Title: Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments
• Authors: Aniket Bhattacharyya, Anurag Tripathi, Ujjal Das, Archan Karmakar, Amit Pathak, Maneesh Gupta,
• Abstract summary: Specialized non-LLM NLP-based solutions typically involve training models using both textual and geometric information.<n>We propose BLOCKIE, a novel LLM-based approach that organizes VRDs into localized, reusable semantic textual segments.<n>Our approach outperforms the state-of-the-art on public VRD benchmarks by 1-3% in F1 scores.
• Score: 0.25289250870065627
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Information extraction (IE) from Visually Rich Documents (VRDs) containing layout features along with text is a critical and well-studied task. Specialized non-LLM NLP-based solutions typically involve training models using both textual and geometric information to label sequences/tokens as named entities or answers to specific questions. However, these approaches lack reasoning, are not able to infer values not explicitly present in documents, and do not generalize well to new formats. Generative LLM-based approaches proposed recently are capable of reasoning, but struggle to comprehend clues from document layout especially in previously unseen document formats, and do not show competitive performance in heterogeneous VRD benchmark datasets. In this paper, we propose BLOCKIE, a novel LLM-based approach that organizes VRDs into localized, reusable semantic textual segments called $\textit{semantic blocks}$, which are processed independently. Through focused and more generalizable reasoning,our approach outperforms the state-of-the-art on public VRD benchmarks by 1-3% in F1 scores, is resilient to document formats previously not encountered and shows abilities to correctly extract information not explicitly present in documents.

Related papers

• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [28.47810405584841]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• Relation-Rich Visual Document Generator for Visual Information Extraction [12.4941229258054]
  We propose a Relation-rIch visual Document GEnerator (RIDGE) that addresses these limitations through a two-stage approach.<n>Our method significantly enhances the performance of document understanding models on various VIE benchmarks.
  arXiv  Detail & Related papers  (2025-04-14T19:19:26Z)
• VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents [30.012487475552575]
  We introduce a new RAG framework, VDocRAG, which can directly understand varied documents and modalities in a unified image format.<n>We also introduce OpenDocVQA, the first unified collection of open-domain document visual question answering datasets.
  arXiv  Detail & Related papers  (2025-04-14T01:50:33Z)
• 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)
• 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)
• DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models [66.91204604417912]
  This study aims to enhance generalizability of small VDU models by distilling knowledge from LLMs. We present a new framework (called DocKD) that enriches the data generation process by integrating external document knowledge. Experiments show that DocKD produces high-quality document annotations and surpasses the direct knowledge distillation approach.
  arXiv  Detail & Related papers  (2024-10-04T00:53:32Z)
• Unified Multimodal Interleaved Document Representation for Retrieval [57.65409208879344]
  We propose a method that holistically embeds documents interleaved with multiple modalities.<n>We merge the representations of segmented passages into one single document representation.<n>We show that our approach substantially outperforms relevant baselines.
  arXiv  Detail & Related papers  (2024-10-03T17:49:09Z)
• PDFTriage: Question Answering over Long, Structured Documents [60.96667912964659]
  Representing structured documents as plain text is incongruous with the user's mental model of these documents with rich structure. We propose PDFTriage that enables models to retrieve the context based on either structure or content. Our benchmark dataset consists of 900+ human-generated questions over 80 structured documents.
  arXiv  Detail & Related papers  (2023-09-16T04:29:05Z)
• Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration [75.47708732473586]
  We propose a layout-aware document-level Information Extraction dataset, LIE, to facilitate the study of extracting both structural and semantic knowledge from visually rich documents. LIE contains 62k annotations of three extraction tasks from 4,061 pages in product and official documents. Empirical results show that layout is critical for VRD-based extraction, and system demonstration also verifies that the extracted knowledge can help locate the answers that users care about.
  arXiv  Detail & Related papers  (2022-07-14T07:59:45Z)
• Robust Document Representations using Latent Topics and Metadata [17.306088038339336]
  We propose a novel approach to fine-tuning a pre-trained neural language model for document classification problems. We generate document representations that capture both text and metadata artifacts in a task manner. Our solution also incorporates metadata explicitly rather than just augmenting them with text.
  arXiv  Detail & Related papers  (2020-10-23T21:52:38Z)

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.